Search

Your search keyword '"pronunciation training"' showing total 83 results
Start Over Descriptor "pronunciation training"

Refine your results

83 results on '"pronunciation training"'

52. A Survey of Corporate Speech Pathologists' Demographic Characteristics, Professional Activities, and Career Satisfaction.

Author

Specht, Nicole M. and Blanchet, Paul G.

Abstract

Purpose: Survey methodology was used to examine a sample of corporate speech pathologists' demographic characteristics, professional activities, and career satisfaction. Method: Forty-one members of the Corporate Speech Pathology Network (CORSPAN) responded to an online survey. Participants described their corporate practices in terms of their professional training, experience, client characteristics, services provided, marketing practices, and job satisfaction. Descriptive statistics were calculated for individual survey items and correlations between pairs of items. Results: In general, respondents reported (a) spending approximately one third of their work-related time in direct client training; (b)employing a variety of marketing tools to promote their corporate speech pathology (CSP) services; and (c) being experienced with accent/dialect modification, articulation/pronunciation, and speech rate modification. Results of paired t tests revealed that participants were significantly more satisfied with their current corporate practice than with their prior work setting. Results provide preliminary quantitative data pertaining to the attributes and activities of the corporate speech pathologist. [ABSTRACT FROM AUTHOR]

Published
2009
Full Text
View/download PDF

53. Automatic Speech Recognition: Reliability and Pedagogical Implications for Teaching Pronunciation.

Author

Kim, In-Seok

Subjects
*AUTOMATIC speech recognition, *PRONUNCIATION, *TEACHING, *ENGLISH language education in universities & colleges, *COMPUTER software, *EDUCATIONAL technology
Abstract

This study examines the reliability of automatic speech recognition (ASR) software used to teach English pronunciation, focusing on one particular piece of software, FluSpeak, as a typical example. Thirty-six Korean English as a Foreign Language (EFL) college students participated in an experiment in which they listened to 15 sentences that appeared in FluSpeak and recorded their voices, repeating sentence by sentence. The ASR software analysis of their production was then compared to pronunciation scores determined by native English speaking (NES) instructors. Although the correlation coefficient for intonation was nearly zero, indicating that ASR technology is still not as accurate as human analysis, the software may be very useful for student practice with aspects of pronunciation. The paper suggests a lesson plan for teaching English pronunciation through ASR software. [ABSTRACT FROM AUTHOR]

Published
2006

54. Lietuvių bendrinės tarties būklė ir lavinimo problemos pradinėje mokykloje.

Author

Bukantienė, Janina

Subjects
ELOCUTION, LINGUISTICS, TEACHING, LANGUAGE & languages, SCHOOL children
Abstract

Copyright of Man & the Word / Zmogus ir zodis is the property of Vytautas Magnus University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Published
2006

55. The effects of embodied shadowing on L2 pronunciation

Author

Tamburini, Valeria

Subjects
Shadowing training, Embodied shadowing, Beat gestures, Pronunciation training, EFL, Fluency, Shadowing technique, Suprasegmentals, Comprehensibility, Accentedness
Abstract

Treball de fi de màster en Lingüística Teòrica i Aplicada. Tutora: Dra. Pilar Prieto Vives. Previous studies have explored the benefits of shadowing in the EFL classroom and have shown that this technique, which consists in repeating what one hears simultaneously, helps improve pronunciation skills. However, very little is known about the potential beneficial effects of performing “embodied shadowing” while mirroring rhythmic beat gestures. This study adopts a between-subjects pre-/post-test design to determine if both observing and reproducing manual beat gestures during shadowing training leads to an improvement in pronunciation in terms of fluency, comprehensibility and accentedness when compared to an onlyshadowing condition. Crucially, the study controls for shadowing performance by participants. Fifty-four students underwent six shadowing training sessions over a two-week span, in which they were asked to shadow English video recorded readings of a comic narration in two conditions, the Gesture and the No-Gesture condition. Shadowing performance was assessed, and participants were divided into two groups, according to their level in shadowing performance. Pronunciation assessments of a reading task before and after training revealed statistically significant improvements in fluency, comprehensibility and accentedness only in good shadowers and across both Gesture and No-Gesture conditions. The results suggest that both embodied and nonembodied shadowing training have a positive effect for improving L2 pronunciation when participants perform shadowing in a simultaneous way.

Published
2020

56. Die Auswirkung von High-Variability-Training auf die Perzeption und Produktion des Gespanntheitskontrasts bei russischsprachigen Deutschlernenden

Author

Mooshammer, Christine, Schumacher, Nicole, Dunzow, Katharina, Mooshammer, Christine, Schumacher, Nicole, and Dunzow, Katharina

Abstract

Es wird untersucht, ob das High-Variability-Training (HVT) die Perzeptions- und Produktionsleistungen des Gespanntheitskontrastes deutscher Vokale bei russischspra-chigen Deutschlernenden positiv beeinflusst. Dafür wurde in Anlehnung an bekannte HVT-Studien ein Aussprachetraining speziell für die Vokaldauer konzipiert. Basis ist die Gegenüberstellung zweier phonetischer Lautkontraste als Minimalpaare der fünf deutschen Vokale (A, E, I, O, U). An dem HVT nahmen dreißig fortgeschrittene russischsprachige Lernende des Deut-schen mit muttersprachlich bedingten Fehlern der L2-Vokalproduktion teil, gemäß dem Lernalter (während bzw. nach der kritischen Phase) in zwei Untersuchungsgruppen (RM1, RM2) getrennt. Die Untersuchung verlief in drei Phasen (Pretest, Training und Posttest). Das Training bestand aus acht Sitzungen von jeweils ca. zwanzig Minuten Dauer. Davor und danach wurden die Produktions- und Perzeptionsfähigkeiten ermittelt. Die Testdaten ergeben, dass 73,3 % der RM1- und 80 % der RM2-Probanden die Perzeptionsleistung der deutschen Vokalphoneme signifikant steigerten. In beiden Gruppen stiegen ebenfalls tendenziell die Produktionsfähigkeiten, 66,7 % der RM1- und 60 % der RM2-Probanden erhöhten sie signifikant. Dennoch konnte kein Teil-nehmer eine Vokalproduktion auf muttersprachlichem Niveau erreichen. Gezieltes HVT-Aussprachetraining wirkt sich demnach positiv auf die Perzeption und Produktion des Gespanntheitskontrastes bei russischsprachigen Deutschlernenden aus und ist eine effektive Erweiterung für den Vokalerwerb auch für fortgeschrittene L2-Lernende. Diese Erkenntnis unterstützt die Ergebnisse der Studien von Logan et al. (1991), Wang et al. (1999), Cenoz & Garciá-Lecumberri (1999), Lambacher et al. (2005), Nishi & Kewley-Port (2007), Iverson & Evans (2009), Liatambur & Lai (2011), Iverson, Pinet & Evans (2012), Wong (2012), Rato (2014), Jügler et al. (2015)., This study investigates whether high variability training (HVT) positively influences perception and production of the tension contrast of German vowels in Russian-speaking learners of German. For this task a pronunciation training course was developed especially for vowel length, drawing on established HVT studies. The basis for this is the comparison of two phonetic contrasts as minimal pairs, taken from the five German vowels (A, E, I, O, U). 30 advanced Russian-speaking learners of German with mother tongue interference in L2 vowel production took part in the HVT, separated according to learning age (during or after the critical phase) into two study groups (RM1, RM2). The study took place in three phases (pre-test, training and post-test). The training consisted of eight sessions, each of approx. 20 minutes in length. Production and perception abilities were tested before and after this. The test results show that 73.3% of the RM1 and 80% of the RM2 test subjects significantly increased their ability to perceive the German vowel phonemes. In both groups the production abilities also tended to rise, with 66.7% of the RM1 and 60% of the RM2 test subjects improving them significantly. However, no participant was able to achieve vowel production at native speaker level. This shows that targeted HVT pronunciation training has a positive effect on the perception and production of tension contrast in Russian-speaking learners of German and is an effective extension for vowel development, also for advanced L2 learners. These findings support the results of studies by Logan et al. (1991), Wang et al. (1999), Cenoz & Garciá-Lecumberri (1999), Lambacher et al. (2005), Nishi & Kewley-Port (2007), Iverson & Evans (2009), Liatambur & Lai (2011), Iverson, Pinet & Evans (2012), Wong (2012), Rato (2014), Jügler et al. (2015).

Published
2019

57. Die Auswirkung von High-Variability-Training auf die Perzeption und Produktion des Gespanntheitskontrasts bei russischsprachigen Deutschlernenden

Author

Dunzow, Katharina, Mooshammer, Christine, and Schumacher, Nicole

Subjects
Perzeption, GB 3029, perception, high variability training, pronunciation training, Produktion, Gespanntheitskontrast, HVT, Vokaldauer, production, ddc:400, vowel length, 400 Sprache, Aussprachetraining, High-Variability-Training
Abstract

Es wird untersucht, ob das High-Variability-Training (HVT) die Perzeptions- und Produktionsleistungen des Gespanntheitskontrastes deutscher Vokale bei russischspra-chigen Deutschlernenden positiv beeinflusst. Dafür wurde in Anlehnung an bekannte HVT-Studien ein Aussprachetraining speziell für die Vokaldauer konzipiert. Basis ist die Gegenüberstellung zweier phonetischer Lautkontraste als Minimalpaare der fünf deutschen Vokale (A, E, I, O, U). An dem HVT nahmen dreißig fortgeschrittene russischsprachige Lernende des Deut-schen mit muttersprachlich bedingten Fehlern der L2-Vokalproduktion teil, gemäß dem Lernalter (während bzw. nach der kritischen Phase) in zwei Untersuchungsgruppen (RM1, RM2) getrennt. Die Untersuchung verlief in drei Phasen (Pretest, Training und Posttest). Das Training bestand aus acht Sitzungen von jeweils ca. zwanzig Minuten Dauer. Davor und danach wurden die Produktions- und Perzeptionsfähigkeiten ermittelt. Die Testdaten ergeben, dass 73,3 % der RM1- und 80 % der RM2-Probanden die Perzeptionsleistung der deutschen Vokalphoneme signifikant steigerten. In beiden Gruppen stiegen ebenfalls tendenziell die Produktionsfähigkeiten, 66,7 % der RM1- und 60 % der RM2-Probanden erhöhten sie signifikant. Dennoch konnte kein Teil-nehmer eine Vokalproduktion auf muttersprachlichem Niveau erreichen. Gezieltes HVT-Aussprachetraining wirkt sich demnach positiv auf die Perzeption und Produktion des Gespanntheitskontrastes bei russischsprachigen Deutschlernenden aus und ist eine effektive Erweiterung für den Vokalerwerb auch für fortgeschrittene L2-Lernende. Diese Erkenntnis unterstützt die Ergebnisse der Studien von Logan et al. (1991), Wang et al. (1999), Cenoz & Garciá-Lecumberri (1999), Lambacher et al. (2005), Nishi & Kewley-Port (2007), Iverson & Evans (2009), Liatambur & Lai (2011), Iverson, Pinet & Evans (2012), Wong (2012), Rato (2014), Jügler et al. (2015). This study investigates whether high variability training (HVT) positively influences perception and production of the tension contrast of German vowels in Russian-speaking learners of German. For this task a pronunciation training course was developed especially for vowel length, drawing on established HVT studies. The basis for this is the comparison of two phonetic contrasts as minimal pairs, taken from the five German vowels (A, E, I, O, U). 30 advanced Russian-speaking learners of German with mother tongue interference in L2 vowel production took part in the HVT, separated according to learning age (during or after the critical phase) into two study groups (RM1, RM2). The study took place in three phases (pre-test, training and post-test). The training consisted of eight sessions, each of approx. 20 minutes in length. Production and perception abilities were tested before and after this. The test results show that 73.3% of the RM1 and 80% of the RM2 test subjects significantly increased their ability to perceive the German vowel phonemes. In both groups the production abilities also tended to rise, with 66.7% of the RM1 and 60% of the RM2 test subjects improving them significantly. However, no participant was able to achieve vowel production at native speaker level. This shows that targeted HVT pronunciation training has a positive effect on the perception and production of tension contrast in Russian-speaking learners of German and is an effective extension for vowel development, also for advanced L2 learners. These findings support the results of studies by Logan et al. (1991), Wang et al. (1999), Cenoz & Garciá-Lecumberri (1999), Lambacher et al. (2005), Nishi & Kewley-Port (2007), Iverson & Evans (2009), Liatambur & Lai (2011), Iverson, Pinet & Evans (2012), Wong (2012), Rato (2014), Jügler et al. (2015).

Published
2019

58. The Use of Multimedia Drills in College Students‟ English Pronunciation Training

Author

Joanalyn C. Estioco and Maylen G. Eroa

Subjects
lcsh:Social Sciences, lcsh:H, multimedia drills, critical English sounds, pronunciation errors, lcsh:Q, lcsh:Science, pronunciation training
Abstract

For a time, pronunciation teaching and practice has been put aside in many English language classrooms perhaps due to the belief that pronunciation is a weak measure of a person’s English proficiency. The declining English proficiency of Filipinos, especially in speaking, is something that needs to be given careful and immediate attention. The response of the education sector in this issue is highly critical and necessary more than ever before. Since higher educational institutions provide the final frontier of education and training before participants become part of the local and international work force, these institutions are in the best position to make significant interventions; thus, this study. This experimental research aims to investigate the effects of using multimedia drills in college students’ English pronunciation training. First, the most common pronunciation errors are identified; second, a pre-test-post-test experiment is performed to test if the use of multimedia drills help minimize the errors; finally, a pronunciation module is developed. The findings of the study reveal that the most common pronunciation errors are /ð/, /z/, /θ/, /æ/, and /i/. Two tests are used in the experiment: listening and speaking tests. In the listening test, the experimental group performs better than the control group; however, in the speaking test, the experimental group also performs better than the control group but the difference is not statistically significant. The effect of the use of multimedia drills on the experimental group is significant for the listening test but not for the speaking test; hence, the multimedia drills has an effect in improving the perception of the critical English sounds but not their production. It is therefore recommended that pronunciation training be conducted for a relatively longer period so that the use of multimedia drills may have a significant effect on the students’ production of English speech sounds especially those which pose the most difficulty.

Published
2015

59. A case study: How do Japanese learners of English learn to use acoustic cues to differentiate stressed and unstressed syllables in pronunciation training ?

Author

TSUSHIMA, Teruaki

Subjects
stress, prosody, nonnative speech production, pronunciation training, pitch
Abstract

As part of a case study of two adult Japanese learners of English, the present study investigated how they learned to use acoustic cues to differentiate English stressed and unstressed syllables through a pronunciation training program. The acoustic cues included F0, intensity, duration and vowel quality (F2-F1). They received pronunciation training focused on English syllable structure, word and sentence stress, consonants and vowels, coupled with reading and speaking practice with special attention to prosody. The results showed that the Japanese learners were able to learn to use F0 and intensity as the acoustic cues, but that it was much more difficult to learn to use duration and vowel quality. Possible accounts of the results and implications for teaching pronunciation are discussed.

Published
2015

60. Speaker-Adaptive Acoustic-Articulatory Inversion using Cascaded Gaussian Mixture Regression

Author

Laurent Girin, Gérard Bailly, Thomas Hueber, Xavier Alameda-Pineda, GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-CRISSP), Département Parole et Cognition (GIPSA-DPC), Grenoble Images Parole Signal Automatique (GIPSA-lab), Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Grenoble Images Parole Signal Automatique (GIPSA-lab), Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), Interpretation and Modelling of Images and Videos (PERCEPTION), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Grenoble Images Parole Signal Automatique (GIPSA-lab), and Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)

Subjects
Acoustics and Ultrasonics, Computer science, speech production, Speech recognition, pronunciation training, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Expectation–maximization algorithm, Computer Science (miscellaneous), Gaussian mixture regression, Electrical and Electronic Engineering, Hidden Markov model, talking head, EM algorithm, Reference model, business.industry, speaker adaptation, Statistical model, Pattern recognition, Mixture model, Speaker recognition, Speaker diarisation, Acoustic space, Computational Mathematics, Artificial intelligence, Acoustic-articulatory inversion, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience; This paper addresses the adaptation of an acoustic-articulatory model of a reference speaker to the voice of another speaker, using a limited amount of audio-only data. In the context of pronunciation training, a virtual talking head displaying the internal speech articulators (e.g., the tongue) could be automatically animated by means of such a model using only the speaker's voice. In this study, the articulatory-acoustic relationship of the reference speaker is modeled by a gaussian mixture model (GMM). To address the speaker adaptation problem, we propose a new framework called cascaded Gaussian mixture regression (C-GMR), and derive two implementations. The first one, referred to as Split-C-GMR, is a straightforward chaining of two distinct GMRs: one mapping the acoustic features of the source speaker into the acoustic space of the reference speaker, and the other estimating the articulatory trajectories with the reference model. In the second implementation, referred to as Integrated-C-GMR, the two mapping steps are tied together in a single probabilistic model. For this latter model, we present the full derivation of the exact EM training algorithm, that explicitly exploits the missing data methodology of machine learning. Other adaptation schemes based on maximum-a posteriori (MAP), maximum likelihood linear regression (MLLR) and direct cross-speaker acoustic-to-articulatory GMR are also investigated. Experiments conducted on two speakers for different amount of adaptation data show the interest of the proposed C-GMR techniques.

Published
2015
Full Text
View/download PDF

62. Comparing the effect of pronunciation and ultrasound trainings to pronunciation training only for the improvement of the production of the French /y/-/u/ contrast by four Japanese learners of French

Author

Kocjančič Antolík, Tanja, Pillot-Loiseau, Claire, Kamiyama, Takeki, Fougeron, Cécile, LPP - Laboratoire de Phonétique et Phonologie - UMR 7018 (LPP), Université Sorbonne Nouvelle - Paris 3-Centre National de la Recherche Scientifique (CNRS), Linguistique Empirique : Cognition, Société et Langage (LECSeL), Transferts critiques anglophones (TransCrit), Université Paris 8 Vincennes-Saint-Denis (UP8)-Université Paris 8 Vincennes-Saint-Denis (UP8), Edinburgh University and Queen Margaret University, ANR-11-IDEX-0005,USPC,Université Sorbonne Paris Cité(2011), Lo Bue, Gwénaëlle, and Université Sorbonne Paris Cité - - USPC2011 - ANR-11-IDEX-0005 - IDEX - VALID

Subjects
u/-/u/ contrast, Ultrasound, Japanese leanerns, [SHS.LANGUE]Humanities and Social Sciences/Linguistics, AFF, [SHS.LANGUE] Humanities and Social Sciences/Linguistics, pronunciation training
Abstract

La publication peut être trouvée au lien suivant:http://www.qmu.ac.uk/casl/conf/ultrafest%5F2013/docs/TKA_Kocjancic-Antolik_1_ultrafest.pdf; International audience; Japanese learners of French commonly have difficulties producing perceptually recognisable French /y/ and /u/. The two sounds are articulatorily different from Japanese /u/, a high non-front vowel in the Tokyo variety with the tongue less retracted and lips less rounded than in French /u/ (Bothorel et al., 1986; Uemura & Takada, 1990). The French /u/ produced by native speakers of Tokyo Japanese is typically perceived as /ø/ by native listeners of French (Kamiyama & Vaissière, 2009). French /u/ and /y/ are phonemically contrastive in Parisian French and are present in a number of minimal pairs. Being able to produce perceptually recognisable French /u/ is thus necessary for Japanese learners, even more so because the more anterior realisations may overlap with French /y/. The two sounds are typically learned by way of perception, but the progress can be slow because of the lack of perceptual differentiation between them. For this reason, it was hypothesised that learners benefit from visual feedback of tongue position by avoiding relying only on perceptual route but rather addressing articulation directly. In total, seven participants took part in the study. The first subject was a 42-year-old female French native, recorded for reference articulatory and acoustic data. The six others were adult female native speakers of Japanese and living in Paris at the time of the study. They all started learning French as adults, were intermediate level learners and, at the time of participation, they were all attending a 12-week French pronunciation course including training sessions in language lab. Four of the participants (experimental group) received three 45-minute training sessions in which ultrasound was used as a visual aid in achieving and controlling the tongue position of the target vowels. The training began with isolated vowels, progressed to non-words with different phonetic contexts (facilitating, neutral and difficult contexts), then on to real words and sentences. The exact protocol was adjusted to the abilities and preferences of each participant. Each of these four participants underwent ultrasound and audio recordings three times: one week before the first training session (pre-training), one week after the last training session (post-training) and two months after the post-training recording (follow-up). The remaining three participants did not receive any ultrasound training (control group) but were also recorded two times: at the beginning and at the end of the pronunciation course. The recorded corpus consisted of ten repetitions of (1) [y] and [u] in isolation, as well as [a], [i] and the Japanese [ɯ] (not recorded in pre-training), (2) alternation between [y] and [u], (3) disyllabic non-words CVCV where V is /y/ or /u/, and C is /p/, /t/ or /k/, (4) 28 real words and (5) four sentences (not recorded in pre-training). The French native speaker was recorded only once. Acoustic and articulatory analyses are under way. In this abstract, we focus on the articulatory data for two of the subjects in the experimental group, the two in the control group and for the native subject. The current analysis of isolated /y/ and /u/ of the two Japanese learners who received ultrasound training confirms the difficulties that Japanese learners of French have with the production of French /y/ and /u/ (Kamiyama and Vaissière 2009). It also shows some improvements both in acoustic and in articulatory (Figure 1) data in post-training: AK shows a clearer separation between the tongue contours for each of the two vowels in the post-training recording, and even a greater distinction in follow-up. CS showed a further posteriorisation of the tongue root for /u/ after the ultrasound trainings (Figure 1), while the tongue shape is similar between the two recordings for both control learners: their /u/ is similar to the Japanese [ɯ] after traditional pronunciation lessons (figure 2). The four Japanese learners who received lessons with ultrasound reported that these sessions were enjoyable and effective for both /y/ and /u/. They said that the image helped them to better control the position of their tongue. 3 of 4 speakers easily understood this image, which helped them a lot. All of them would take some lessons with ultrasound to better articulate other French sounds. This study is a first step. Further analysis of the available data will allow inspecting articulatory improvements in more varied contexts (words vs. nonwords, mono-vs. disyllabic words, isolated vowels vs. words vs. sentences) as well as in more quantitative details (tongue height and curvature, tongue curvature position, Ménard et al. 2012; Dorsum Excursion Index DEI, Zharkova 2013, among others parameters). The method will also be useful for the analysis of other kinds of productions such as the singing voice.

Published
2013

63. Uttalsträning i svenska för tre personer med thai som förstaspråk : En single subject design-studie

Author

Lööf, Maja and Svensson, Erika

Subjects
intelligibility, förståelighet, Pronunciation training, svenska som andraspråk, suprasegmentell, segmental, suprasegmental, Swedish as second language, Uttalsträning, Thai, segmentell
Abstract

I föreliggande single subject designstudie har tre personer med thai som modersmål och svenska som andraspråk tränats specifikt i svenskt uttal. Syftet med föreliggande studie var därför att utforma samt genomföra en uttalsintervention vilken delades in i en suprasegmentell och en segmentell modul. Syftet var vidare att undersöka hur suprasegmentella och segmentella förändringar i uttalet påverkade uttalets förståelighet. Uttalsträningen utfördes 14 gånger under en fem-veckors period. Interventionen delades upp i två moduler, en med suprasegmentellt fokus (B1) och en med segmentellt fokus (B2). I den suprasegmentella modulen ingick medvetandegörelse av stavelseuppbyggnad samt träning i svenska betoningsmönster. Den segmentella modulen innefattade träning av konsonantförbindelser, [ɧ] samt /r/. Efter varje tillfälle fick deltagarna repetera 50 ord som valts ut innan studiens början. Dessa ord analyserades utifrån deltagarnas förmåga att korrekt producera suprasegmentella och segmentella aspekter och utgjorde studiens mätpunkter. De suprasegmentella aspekterna bedömdes utifrån uppsatta bedömningskriterier och de segmentella aspekterna bedömdes med hjälp av Percentage Phonemes Correct (PPC). Efter genomförd intervention fick tre utomstående lyssnare skatta förståelighet för att undersöka om samband kunde ses mellan deras skattningar och de valda bedömningsverktygen. Enskilda ord ur ordlistorna valdes ut för att bedömningsverktygen även skulle jämföras mot akustiska mätningar. Resultaten i föreliggande studie visade på att samband kunde ses mellan specifik uttalsträning med segmentellt fokus och förbättrat uttal både vad gäller segmentella och suprasegmentella aspekter. Samma resultat visade den suprasegmentella uttalsträningen ge. Vidare kunde samband ses mellan bedömningen av de segmentella aspekterna utifrån mätpunkternas beräknade PPC och förståelighetsskattningarna. När PPC ökade förbättrades också förståeligheten. Då uttalsträning bör ha som fokus att uppnå god förståelighet hos andraspråksinläraren (Pennington, 1996; Levis, 2005) föreslås att segmentella aspekter bör ingå i uttalsträning. Mellan förbättringarna av suprasegmentella aspekter och förståelighet har inte liknande samband kunnat ses vilket dock kan bero på studiens design. Författarna till föreliggande studie anser därför att suprasegmentella aspekter i uttalsträning inte bör bortprioriteras. Three native Thai speakers with Swedish as their second language have received special training in Swedish pronunciation in the current single-subject design study. The aim of the current study was therefore to devise and implement a set of pronunciation training exercises, divided into suprasegmental and segmental modules. The aim was also to examine how suprasegmental and segmental changes in pronunciation affected the intelligibility of the pronunciation. The pronunciation training consisted of 14 training sessions during a five-week period. The exercises were divided into two modules, one with focus on suprasegmental aspects (B1) and one with focus on segmental aspects (B2). The suprasegmental module included acquainting subjects with the syllabic structure of the Swedish language as well as training of the Swedish language stress pattern. The segmental module contained training of consonant clusters, the Swedish speech sound [ɧ] and /r/. At the end of each session the participants were asked to repeat 50 words chosen before the start of the study. These words constituted the measuring points of the study and were analyzed according to the participants' ability to produce suprasegmental and segmental aspects correctly. The suprasegmental aspects were assessed according to fixed criteria and the segmental aspects were rated by means of Percentage Phonemes Correct (PPC). After completion of the final training session, three independent listeners estimated intelligibility to determine if relationship existed between these and the chosen assessment tools. Single words were selected in order to compare their criteria-based and PPC-ratings with acoustic correlates. The results of the present study indicate that a relationship can be observed between specific pronunciation training with focus on segmental aspects and improved pronunciation in terms of segmental and suprasegmental aspects. The pronunciation training with suprasegmental focus indicated the same conclusion. Further, a relationship can be seen between the judgment of the segmental aspects based on the measuring points' PPC-rating and the ratings of intelligibility. The intelligibility improved when the PPC increased. The focus of pronunciation training should be to achieve good intelligibility (Pennington, 1996; Levis, 2005); therefore it is suggested that segmental aspects should be included in pronunciation training for native Thai speakers when learning Swedish as a second language. No similar relations have been discovered between the suprasegmental aspects and intelligibility, which, however, may be due to limitations in the design of the study. Therefore suprasegmental aspects should not be neglected in pronunciation training.

Published
2013

64. Embodied conversational agents in Computer Assisted Language Learning

Author

Preben Wik and Anna Hjalmarsson

Subjects
Linguistics and Language, Vocabulary, Computer science, media_common.quotation_subject, Pronunciation, computer.software_genre, pronunciation training, Language and Linguistics, CALL, CAPT, media_common, 060201 languages & linguistics, Communication, 05 social sciences, 050301 education, 06 humanities and the arts, Language acquisition, Linguistics, Computer Science Applications, Embodied agent, Embodied cognition, Modeling and Simulation, Second langue learning, 0602 languages and literature, dialogue systems, Computer Vision and Pattern Recognition, Language teacher, embodied conversational agents, 0503 education, computer, Software
Abstract

International audience; This paper describes two systems using embodied conversational agents (ECAs) for language learning. The first system, called Ville, is a virtual language teacher for vocabulary and pronunciation training. The second system, a dialogue system called DEAL, is a role-playing game for practicing conversational skills. Whereas DEAL acts as a conversational partner with the objective of creating and keeping an interesting dialogue, Ville takes the role of a teacher who guides, encourages and gives feedback to the students.

Published
2009
Full Text
View/download PDF

65. Embodied conversational agents in computer assisted language learning

Author

Wik, Preben, Hjalmarsson, Anna, Wik, Preben, and Hjalmarsson, Anna

Abstract

This paper describes two systems using embodied conversational agents (ECAs) for language learning. The first system, called Ville, is a virtual language teacher for vocabulary and pronunciation training. The second system, a dialogue system called DEAL, is a role-playing game for practicing conversational skills. Whereas DEAL acts as a conversational partner with the objective of creating and keeping an interesting dialogue, Ville takes the role of a teacher who guides, encourages and gives feedback to the students., QC 20120109. tmh_import_11_12_14

Published
2009
Full Text
View/download PDF

66. Can audio-visual instructions help learners improve their articulation? : an ultrasound study of short term changes

Author

Engwall, Olov and Engwall, Olov

Abstract

This paper describes how seven French subjects change their pronunciation and articulation when practising Swedish words with a computer-animated virtual teacher. The teacher gives feedback on the user's pronunciation with audiovisual instructions suggesting how the articulation should be changed. A wizard-of-Oz set-up was used for the training session, in which a human listener choose the adequate pre-generated feedback based on the user's pronunciation. The subjects change of the articulation was monitored during the practice session with a hand-held ultrasound probe. The perceptual analysis indicates that the subjects improved their pronunciation during the training and the ultrasound measurements suggest that the improvement was made by following the articulatory instructions given by the computer-animated teacher., QC 20110222

Published
2008

67. Audio-psycho-phonology as an aim to improve the pronunciation of the English of Zulu speakers : an evaluation

Author

Lemmer, Karina, Wissing, D.P., and 10171347 - Wissing, Daniel Petrus (Supervisor)

Subjects
Zulu-speakers, Tomatis, Second language pronunciation, Pronunciation training, Audio-psycho-phonology
Abstract

Thesis (M.A. (English))--Potchefstroom University for Christian Higher Education, 2001. This study investigates the impact of Audio-psycho-phonology (APP), a process of hearing stimulation by means of a devise called the Electronic Ear, as an aid to second language (L2) pronunciation training. The outcomes of APP and traditional pronunciation training on the vowel perception L 1 Zulu-speakers who use English as a business language were explored. This group was chosen because intelligible pronunciation is important in their designations. Perception of English vowels was isolated as a base for testing. Pre- and post testing of vowel perception indicates that APP did not have a significant impact as an aid to pronunciation training. A post hoc attitude assessment, conducted amongst the business community, yielded interesting results regarding the connection between pronunciation and language attitudes. Masters

Published
2001

69. Phonological Processes in Sentences Produced by Adult Japanese English Language Learners

Author

Schrock, Lana Renee

Subjects
Speech Therapy, phonological processes, Japanese, English Language Learners, pronunciation training, speech-language pathology
Abstract

This paper examined the speech sound errors in the sentences of five adult Japanese English Langue Learners (ELLs) and classified the errors as phonological processes. The processes observed were compared to the established developmental processes exhibited by monolingual English speaking children to provide insight into the similarities between L1 phonological acquisition and L2 phonological learning. The results revealed that a majority of the incorrect phonemes are also phonemes that are mastered late in the development of English speaking children. A great deal of variation in rate of occurrence of different phonological processes existed across speakers. Rounding, tensing, decentralization, vowelization, final devoicing, and cluster reduction were the most frequently occurring vowel and consonant processes. The results of this study are interpreted in relation to markedness and a contrastive analysis between Japanese and English phonetic inventories. Clinical implications with respect to pronunciation instruction for ELLs are also addressed.

Published
2013

70. An action research study of pronunciation training, language learning strategies and speaking confidence

Author

Varasarin, Patchara

Subjects
School of Education, 420000 Language and Culture, English language, pronunciation training, language learning strategies, speaking skills, Thailand
Abstract

English is a vehicle for international communication. In order to meet the demands of modern society, English teachers need to pay more attention to the development of learners’ competence and focus on a more effective and successful method. However traditional approaches to English language teaching still dominate Thai classrooms. Language teachers should not focus on reciting but should teach from their own understanding of language learning and help learners gain more competence with confidence. This study is a collaborative action research investigation to develop pronunciation training and communicative competence for Thai students studying English in Thailand. This study investigated pronunciation training and language learning strategies, how they influenced the learning behaviour of Thai students studying English and improved their speaking confidence. The purpose of the training was to improve students’ pronunciation and spoken intelligibility. It drew upon data collected in pronunciation training in one school in Thailand using language learning strategies and evaluated improvement after being trained in developing speaking confidence. The project contained two cycles, the first of which was to train five teachers using pronunciation training and language learning strategies. We evaluated their improvement in correct speech and in developing speaking confidence. In the second cycle, these teachers in turn taught a group of four students each and similar improvements were observed. The action phases showed the implications of the importance of pronunciation training in the Thai context and the usefulness of dictionary usage to help learners to improve their competence and to have more confidence to speak English. The project resulted in a change of policy by the school to include pronunciation teaching and to allocate English classes to teachers who understood that process. The pronunciation learning strategies in this study and those of other researchers were presented to formulate strategies as a contribution for teachers to include teaching pronunciation in their classroom instruction. The researcher intends that the data will be useful for language teachers to help them further their understanding of their students’ learning behaviour to achieve improved pronunciation. In addition, the phonetic symbol system used in the training was chiefly inspired from the symbols of the International Phonetic Association (IPA) to be standardized and easy to apply.

Published
2007

71. Unsupervised Neural Pattern Classifiers for Oral Vowel Pronunciation of Foreign-Accented Speech

Author

Hecker, Joseph

Subjects
pronunciation training, neural gas, unsupervised learning, computer assisted language learning, Electrical and Computer Engineering
Abstract

This thesis describes the development of unsupervised neural-based pattern classifiers for the training of vowel pronunciations for students learning a foreign language. This paper examines American learners of the French language. A corpus of single word utterances is compiled from a group of native French speakers. Cepstral features are used to train two unsupervised neural pattern classifiers: a self-organizing map and a growing neural gas. The development and justification for the use of these classifiers is presented. The output from the classifier is translated to a bar graph for visual assessment. The degree to which the utterance sounds native is determined by comparing target graphs and those produced by the user. It is concluded that unsupervised classification techniques can be used to develop a pronunciation training system that is independent of the language used to train the system. This allows for pronunciation training to be easily achieved for low-density languages.

Published
2006

72. Webová služba pro trénování a výuku výslovnosti cizích jazyků

Author

Szőke, Igor, Bambušek, David, Stehlík, Ján, Szőke, Igor, Bambušek, David, and Stehlík, Ján

Abstract

Táto práca prezentuje návrh a implementáciu webovej aplikácie , ktorá slúži na trénovanie výslovnosti Anglického jazyka . V súčastnosti existuje množstvo on-line služieb , ktorých cieľom je pomôcť užívateľom zlepšiť ich úroveň Anglického jazyka alebo akéhokoľvek iného cudzieho jazyka . Na druhej strane , aplikácií , ktoré by pomohli s výslovnosťou daného jazyka nieje mnoho . Tento projekt bol vyvinutý aby túto dieru zaplátal a aby umožnil užívateľom cvičiť výslovnosť opakovaním krátkych videoukážok . Reč užívateľa bude nahraná pomocou jeho mikrofónu a následne porovnaná s referenčnou nahrávkou . Výsledkom tohto porovnania bude skóre podobnosti , ktoré bude vrátene používateľovi . Skóre podobnosti bude vypočítané použitím algoritmu Dynamic Time Warping, ktorý je zabudovaný vo video prehrávači použitom v tejto aplikácii ., This article presents a design and an implementation of Web application for English pronunciation training. Nowadays, there are a lot of on-line applications that help to improve English level or skill level of any other foreign language. On the other hand, there are not so many applications that help to improve pronunciation of given language. This project was developed to fill the gap, and to enable users to practice pronunciation by repeating short video segments. Using their microphone device users will record their speech. This speech will be compared with the reference recording. Result of this comparison will be returned to the user as a similarity score. The similarity score is computed using Dynamic Time Warping algorithm, that is incorporated inside a video player used in this application.

73. Webová služba pro trénování a výuku výslovnosti cizích jazyků

Author

Szőke, Igor, Bambušek, David, Stehlík, Ján, Szőke, Igor, Bambušek, David, and Stehlík, Ján

Abstract

Táto práca prezentuje návrh a implementáciu webovej aplikácie , ktorá slúži na trénovanie výslovnosti Anglického jazyka . V súčastnosti existuje množstvo on-line služieb , ktorých cieľom je pomôcť užívateľom zlepšiť ich úroveň Anglického jazyka alebo akéhokoľvek iného cudzieho jazyka . Na druhej strane , aplikácií , ktoré by pomohli s výslovnosťou daného jazyka nieje mnoho . Tento projekt bol vyvinutý aby túto dieru zaplátal a aby umožnil užívateľom cvičiť výslovnosť opakovaním krátkych videoukážok . Reč užívateľa bude nahraná pomocou jeho mikrofónu a následne porovnaná s referenčnou nahrávkou . Výsledkom tohto porovnania bude skóre podobnosti , ktoré bude vrátene používateľovi . Skóre podobnosti bude vypočítané použitím algoritmu Dynamic Time Warping, ktorý je zabudovaný vo video prehrávači použitom v tejto aplikácii ., This article presents a design and an implementation of Web application for English pronunciation training. Nowadays, there are a lot of on-line applications that help to improve English level or skill level of any other foreign language. On the other hand, there are not so many applications that help to improve pronunciation of given language. This project was developed to fill the gap, and to enable users to practice pronunciation by repeating short video segments. Using their microphone device users will record their speech. This speech will be compared with the reference recording. Result of this comparison will be returned to the user as a similarity score. The similarity score is computed using Dynamic Time Warping algorithm, that is incorporated inside a video player used in this application.

74. Využití řečových technologií při výuce výslovnosti cizích jazyků

Author

Szőke, Igor, Žmolíková, Kateřina, Barotová, Štěpánka, Szőke, Igor, Žmolíková, Kateřina, and Barotová, Štěpánka

Abstract

Tato diplomová práce pojednává o využití algoritmu Dynamic Time Warping (DTW) pro automatické hodnocení výslovnosti anglického jazyka. Práce se zaměřuje na vylepšení již existující aplikace pro výuku výslovnosti, a to ve třech oblastech: uživatelské rozhraní, samotný algoritmus a korektivní zpětná vazba uživateli. První část se věnuje přehledu technik používaných v této oblasti, následně je představen nový design uživatelského rozhraní, popsán navržený systém a experimenty. Experimenty se zaměřují na problematiku detekce chyb na úrovni fonémů, na detekci chyb v primárním důrazu na úrovni slabik a na hodnocení intonace na úrovni slov. Všechny použité metody jsou navrženy tak, aby poskytovaly korektivní zpětnou vazbu uživateli. V poslední části je popsáno, jak byly všechny tři vylepšené oblasti aplikace otestovány., This diploma thesis deals with automatic English pronunciation assessment and error detection based on the Dynamic Time Warping (DTW) algorithm. It focuses on the improvement of an existing pronunciation training application and it proposes three areas of improvement: user interface, algorithm and corrective feedback. After various methods used for pronunciation assessment are discussed in the first part, the new design is introduced, the proposed system is described and three sets of experiments are performed. The experiments focus on phoneme-level error detection, syllable-level primary stress error detection and word-level intonation assessment and they are designed to be able to provide corrective feedback to the user. The last part of the thesis describes how all three areas of improvement were tested.

75. Využití řečových technologií při výuce výslovnosti cizích jazyků

Author

Szőke, Igor, Žmolíková, Kateřina, Barotová, Štěpánka, Szőke, Igor, Žmolíková, Kateřina, and Barotová, Štěpánka

Abstract

Tato diplomová práce pojednává o využití algoritmu Dynamic Time Warping (DTW) pro automatické hodnocení výslovnosti anglického jazyka. Práce se zaměřuje na vylepšení již existující aplikace pro výuku výslovnosti, a to ve třech oblastech: uživatelské rozhraní, samotný algoritmus a korektivní zpětná vazba uživateli. První část se věnuje přehledu technik používaných v této oblasti, následně je představen nový design uživatelského rozhraní, popsán navržený systém a experimenty. Experimenty se zaměřují na problematiku detekce chyb na úrovni fonémů, na detekci chyb v primárním důrazu na úrovni slabik a na hodnocení intonace na úrovni slov. Všechny použité metody jsou navrženy tak, aby poskytovaly korektivní zpětnou vazbu uživateli. V poslední části je popsáno, jak byly všechny tři vylepšené oblasti aplikace otestovány., This diploma thesis deals with automatic English pronunciation assessment and error detection based on the Dynamic Time Warping (DTW) algorithm. It focuses on the improvement of an existing pronunciation training application and it proposes three areas of improvement: user interface, algorithm and corrective feedback. After various methods used for pronunciation assessment are discussed in the first part, the new design is introduced, the proposed system is described and three sets of experiments are performed. The experiments focus on phoneme-level error detection, syllable-level primary stress error detection and word-level intonation assessment and they are designed to be able to provide corrective feedback to the user. The last part of the thesis describes how all three areas of improvement were tested.

76. Využití řečových technologií při výuce výslovnosti cizích jazyků

Author

Szőke, Igor, Žmolíková, Kateřina, Szőke, Igor, and Žmolíková, Kateřina

Abstract

Tato diplomová práce pojednává o využití algoritmu Dynamic Time Warping (DTW) pro automatické hodnocení výslovnosti anglického jazyka. Práce se zaměřuje na vylepšení již existující aplikace pro výuku výslovnosti, a to ve třech oblastech: uživatelské rozhraní, samotný algoritmus a korektivní zpětná vazba uživateli. První část se věnuje přehledu technik používaných v této oblasti, následně je představen nový design uživatelského rozhraní, popsán navržený systém a experimenty. Experimenty se zaměřují na problematiku detekce chyb na úrovni fonémů, na detekci chyb v primárním důrazu na úrovni slabik a na hodnocení intonace na úrovni slov. Všechny použité metody jsou navrženy tak, aby poskytovaly korektivní zpětnou vazbu uživateli. V poslední části je popsáno, jak byly všechny tři vylepšené oblasti aplikace otestovány., This diploma thesis deals with automatic English pronunciation assessment and error detection based on the Dynamic Time Warping (DTW) algorithm. It focuses on the improvement of an existing pronunciation training application and it proposes three areas of improvement: user interface, algorithm and corrective feedback. After various methods used for pronunciation assessment are discussed in the first part, the new design is introduced, the proposed system is described and three sets of experiments are performed. The experiments focus on phoneme-level error detection, syllable-level primary stress error detection and word-level intonation assessment and they are designed to be able to provide corrective feedback to the user. The last part of the thesis describes how all three areas of improvement were tested.

77. Webová služba pro trénování a výuku výslovnosti cizích jazyků

Author

Szőke, Igor, Bambušek, David, Szőke, Igor, and Bambušek, David

Abstract

Táto práca prezentuje návrh a implementáciu webovej aplikácie , ktorá slúži na trénovanie výslovnosti Anglického jazyka . V súčastnosti existuje množstvo on-line služieb , ktorých cieľom je pomôcť užívateľom zlepšiť ich úroveň Anglického jazyka alebo akéhokoľvek iného cudzieho jazyka . Na druhej strane , aplikácií , ktoré by pomohli s výslovnosťou daného jazyka nieje mnoho . Tento projekt bol vyvinutý aby túto dieru zaplátal a aby umožnil užívateľom cvičiť výslovnosť opakovaním krátkych videoukážok . Reč užívateľa bude nahraná pomocou jeho mikrofónu a následne porovnaná s referenčnou nahrávkou . Výsledkom tohto porovnania bude skóre podobnosti , ktoré bude vrátene používateľovi . Skóre podobnosti bude vypočítané použitím algoritmu Dynamic Time Warping, ktorý je zabudovaný vo video prehrávači použitom v tejto aplikácii ., This article presents a design and an implementation of Web application for English pronunciation training. Nowadays, there are a lot of on-line applications that help to improve English level or skill level of any other foreign language. On the other hand, there are not so many applications that help to improve pronunciation of given language. This project was developed to fill the gap, and to enable users to practice pronunciation by repeating short video segments. Using their microphone device users will record their speech. This speech will be compared with the reference recording. Result of this comparison will be returned to the user as a similarity score. The similarity score is computed using Dynamic Time Warping algorithm, that is incorporated inside a video player used in this application.

78. Webová služba pro trénování a výuku výslovnosti cizích jazyků

Author

Szőke, Igor, Bambušek, David, Szőke, Igor, and Bambušek, David

Abstract

Táto práca prezentuje návrh a implementáciu webovej aplikácie , ktorá slúži na trénovanie výslovnosti Anglického jazyka . V súčastnosti existuje množstvo on-line služieb , ktorých cieľom je pomôcť užívateľom zlepšiť ich úroveň Anglického jazyka alebo akéhokoľvek iného cudzieho jazyka . Na druhej strane , aplikácií , ktoré by pomohli s výslovnosťou daného jazyka nieje mnoho . Tento projekt bol vyvinutý aby túto dieru zaplátal a aby umožnil užívateľom cvičiť výslovnosť opakovaním krátkych videoukážok . Reč užívateľa bude nahraná pomocou jeho mikrofónu a následne porovnaná s referenčnou nahrávkou . Výsledkom tohto porovnania bude skóre podobnosti , ktoré bude vrátene používateľovi . Skóre podobnosti bude vypočítané použitím algoritmu Dynamic Time Warping, ktorý je zabudovaný vo video prehrávači použitom v tejto aplikácii ., This article presents a design and an implementation of Web application for English pronunciation training. Nowadays, there are a lot of on-line applications that help to improve English level or skill level of any other foreign language. On the other hand, there are not so many applications that help to improve pronunciation of given language. This project was developed to fill the gap, and to enable users to practice pronunciation by repeating short video segments. Using their microphone device users will record their speech. This speech will be compared with the reference recording. Result of this comparison will be returned to the user as a similarity score. The similarity score is computed using Dynamic Time Warping algorithm, that is incorporated inside a video player used in this application.

79. Využití řečových technologií při výuce výslovnosti cizích jazyků

Author

Szőke, Igor, Žmolíková, Kateřina, Szőke, Igor, and Žmolíková, Kateřina

Abstract

Tato diplomová práce pojednává o využití algoritmu Dynamic Time Warping (DTW) pro automatické hodnocení výslovnosti anglického jazyka. Práce se zaměřuje na vylepšení již existující aplikace pro výuku výslovnosti, a to ve třech oblastech: uživatelské rozhraní, samotný algoritmus a korektivní zpětná vazba uživateli. První část se věnuje přehledu technik používaných v této oblasti, následně je představen nový design uživatelského rozhraní, popsán navržený systém a experimenty. Experimenty se zaměřují na problematiku detekce chyb na úrovni fonémů, na detekci chyb v primárním důrazu na úrovni slabik a na hodnocení intonace na úrovni slov. Všechny použité metody jsou navrženy tak, aby poskytovaly korektivní zpětnou vazbu uživateli. V poslední části je popsáno, jak byly všechny tři vylepšené oblasti aplikace otestovány., This diploma thesis deals with automatic English pronunciation assessment and error detection based on the Dynamic Time Warping (DTW) algorithm. It focuses on the improvement of an existing pronunciation training application and it proposes three areas of improvement: user interface, algorithm and corrective feedback. After various methods used for pronunciation assessment are discussed in the first part, the new design is introduced, the proposed system is described and three sets of experiments are performed. The experiments focus on phoneme-level error detection, syllable-level primary stress error detection and word-level intonation assessment and they are designed to be able to provide corrective feedback to the user. The last part of the thesis describes how all three areas of improvement were tested.

80. Využití řečových technologií při výuce výslovnosti cizích jazyků

Author

Szőke, Igor, Žmolíková, Kateřina, Szőke, Igor, and Žmolíková, Kateřina

Abstract

Tato diplomová práce pojednává o využití algoritmu Dynamic Time Warping (DTW) pro automatické hodnocení výslovnosti anglického jazyka. Práce se zaměřuje na vylepšení již existující aplikace pro výuku výslovnosti, a to ve třech oblastech: uživatelské rozhraní, samotný algoritmus a korektivní zpětná vazba uživateli. První část se věnuje přehledu technik používaných v této oblasti, následně je představen nový design uživatelského rozhraní, popsán navržený systém a experimenty. Experimenty se zaměřují na problematiku detekce chyb na úrovni fonémů, na detekci chyb v primárním důrazu na úrovni slabik a na hodnocení intonace na úrovni slov. Všechny použité metody jsou navrženy tak, aby poskytovaly korektivní zpětnou vazbu uživateli. V poslední části je popsáno, jak byly všechny tři vylepšené oblasti aplikace otestovány., This diploma thesis deals with automatic English pronunciation assessment and error detection based on the Dynamic Time Warping (DTW) algorithm. It focuses on the improvement of an existing pronunciation training application and it proposes three areas of improvement: user interface, algorithm and corrective feedback. After various methods used for pronunciation assessment are discussed in the first part, the new design is introduced, the proposed system is described and three sets of experiments are performed. The experiments focus on phoneme-level error detection, syllable-level primary stress error detection and word-level intonation assessment and they are designed to be able to provide corrective feedback to the user. The last part of the thesis describes how all three areas of improvement were tested.

81. Webová služba pro trénování a výuku výslovnosti cizích jazyků

Author

Szőke, Igor, Bambušek, David, Szőke, Igor, and Bambušek, David

Abstract

Táto práca prezentuje návrh a implementáciu webovej aplikácie , ktorá slúži na trénovanie výslovnosti Anglického jazyka . V súčastnosti existuje množstvo on-line služieb , ktorých cieľom je pomôcť užívateľom zlepšiť ich úroveň Anglického jazyka alebo akéhokoľvek iného cudzieho jazyka . Na druhej strane , aplikácií , ktoré by pomohli s výslovnosťou daného jazyka nieje mnoho . Tento projekt bol vyvinutý aby túto dieru zaplátal a aby umožnil užívateľom cvičiť výslovnosť opakovaním krátkych videoukážok . Reč užívateľa bude nahraná pomocou jeho mikrofónu a následne porovnaná s referenčnou nahrávkou . Výsledkom tohto porovnania bude skóre podobnosti , ktoré bude vrátene používateľovi . Skóre podobnosti bude vypočítané použitím algoritmu Dynamic Time Warping, ktorý je zabudovaný vo video prehrávači použitom v tejto aplikácii ., This article presents a design and an implementation of Web application for English pronunciation training. Nowadays, there are a lot of on-line applications that help to improve English level or skill level of any other foreign language. On the other hand, there are not so many applications that help to improve pronunciation of given language. This project was developed to fill the gap, and to enable users to practice pronunciation by repeating short video segments. Using their microphone device users will record their speech. This speech will be compared with the reference recording. Result of this comparison will be returned to the user as a similarity score. The similarity score is computed using Dynamic Time Warping algorithm, that is incorporated inside a video player used in this application.

82. Webová služba pro trénování a výuku výslovnosti cizích jazyků

Author

Szőke, Igor, Bambušek, David, Stehlík, Ján, Szőke, Igor, Bambušek, David, and Stehlík, Ján

Abstract

Táto práca prezentuje návrh a implementáciu webovej aplikácie , ktorá slúži na trénovanie výslovnosti Anglického jazyka . V súčastnosti existuje množstvo on-line služieb , ktorých cieľom je pomôcť užívateľom zlepšiť ich úroveň Anglického jazyka alebo akéhokoľvek iného cudzieho jazyka . Na druhej strane , aplikácií , ktoré by pomohli s výslovnosťou daného jazyka nieje mnoho . Tento projekt bol vyvinutý aby túto dieru zaplátal a aby umožnil užívateľom cvičiť výslovnosť opakovaním krátkych videoukážok . Reč užívateľa bude nahraná pomocou jeho mikrofónu a následne porovnaná s referenčnou nahrávkou . Výsledkom tohto porovnania bude skóre podobnosti , ktoré bude vrátene používateľovi . Skóre podobnosti bude vypočítané použitím algoritmu Dynamic Time Warping, ktorý je zabudovaný vo video prehrávači použitom v tejto aplikácii ., This article presents a design and an implementation of Web application for English pronunciation training. Nowadays, there are a lot of on-line applications that help to improve English level or skill level of any other foreign language. On the other hand, there are not so many applications that help to improve pronunciation of given language. This project was developed to fill the gap, and to enable users to practice pronunciation by repeating short video segments. Using their microphone device users will record their speech. This speech will be compared with the reference recording. Result of this comparison will be returned to the user as a similarity score. The similarity score is computed using Dynamic Time Warping algorithm, that is incorporated inside a video player used in this application.

Catalog

Books, media, physical & digital resources
See catalog results