Search

Your search keyword '"Rudzicz, Frank"' showing total 740 results
Start Over Author "Rudzicz, Frank"

Refine your results

740 results on '"Rudzicz, Frank"'

251. On the importance of normative data in speech-based assessment

Author

Noorian, Zeinab, Pou-Prom, Chlo��, and Rudzicz, Frank

Subjects
FOS: Computer and information sciences, Computer Science - Computation and Language, Computation and Language (cs.CL)
Abstract

Data sets for identifying Alzheimer's disease (AD) are often relatively sparse, which limits their ability to train generalizable models. Here, we augment such a data set, DementiaBank, with each of two normative data sets, the Wisconsin Longitudinal Study and Talk2Me, each of which employs a speech-based picture-description assessment. Through minority class oversampling with ADASYN, we outperform state-of-the-art results in binary classification of people with and without AD in DementiaBank. This work highlights the effectiveness of combining sparse and difficult-to-acquire patient data with relatively large and easily accessible normative datasets.

Published
2017

260. Speech in Smartwatch based Audio

Author

Liaqat, Daniyal, primary, Wu, Robert, additional, Gershon, Andrea, additional, Alshaer, Hisham, additional, Rudzicz, Frank, additional, and de Lara, Eyal, additional

Published
2018
Full Text
View/download PDF

265. SLPAT 2016 Workshop on Speech and Language Processing for Assistive Technologies

Author

Christensen, Heidi, Portet, François, Quatieri, Thomas, Rudzicz, Frank, Vertanen, Keith, Department of Computer Sciences [Scheffield], University of Sheffield [Sheffield], Laboratoire d'Informatique de Grenoble ( LIG ), Université Pierre Mendès France - Grenoble 2 ( UPMF ) -Université Joseph Fourier - Grenoble 1 ( UJF ) -Institut National Polytechnique de Grenoble ( INPG ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Grenoble Alpes ( UGA ), Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole ( GETALP ), Université Pierre Mendès France - Grenoble 2 ( UPMF ) -Université Joseph Fourier - Grenoble 1 ( UJF ) -Institut National Polytechnique de Grenoble ( INPG ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Grenoble Alpes ( UGA ) -Université Pierre Mendès France - Grenoble 2 ( UPMF ) -Université Joseph Fourier - Grenoble 1 ( UJF ) -Institut National Polytechnique de Grenoble ( INPG ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Grenoble Alpes ( UGA ), MIT Lincoln Laboratory, Massachusetts Institute of Technology ( MIT ), University of Toronto, Toronto Rehabilitation Institute [Toronto], University Health Network, Michigan Technological University ( MTU ), ACL/ISCA Special Interest Group on Speech and Language Processing for Assistive Technologies (SIG-SLPAT), Laboratoire d'Informatique de Grenoble (LIG ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole (GETALP ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Massachusetts Institute of Technology (MIT), and Michigan Technological University (MTU)

Subjects
[ INFO.INFO-AI ] Computer Science [cs]/Artificial Intelligence [cs.AI], ComputingMilieux_MISCELLANEOUS, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

International audience

Published
2016
Full Text
View/download PDF

266. Predicting health inspection results from online restaurant reviews

Author

Wong, Samantha, Chinaei, Hamidreza, and Rudzicz, Frank

Subjects
FOS: Computer and information sciences, Computer Science - Learning, Computer Science - Computation and Language, Computation and Language (cs.CL), Machine Learning (cs.LG)
Abstract

Informatics around public health are increasingly shifting from the professional to the public spheres. In this work, we apply linguistic analytics to restaurant reviews, from Yelp, in order to automatically predict official health inspection reports. We consider two types of feature sets, i.e., keyword detection and topic model features, and use these in several classification methods. Our empirical analysis shows that these extracted features can predict public health inspection reports with over 90% accuracy using simple support vector machines., Comment: 7 pages, 2 figures, 2 tables

Published
2016
Full Text
View/download PDF

267. Sex, drugs, and violence

Author

Raimondo, Stefania and Rudzicz, Frank

Subjects
FOS: Computer and information sciences, Computer Science - Computation and Language, Computation and Language (cs.CL)
Abstract

Automatically detecting inappropriate content can be a difficult NLP task, requiring understanding context and innuendo, not just identifying specific keywords. Due to the large quantity of online user-generated content, automatic detection is becoming increasingly necessary. We take a largely unsupervised approach using a large corpus of narratives from a community-based self-publishing website and a small segment of crowd-sourced annotations. We explore topic modelling using latent Dirichlet allocation (and a variation), and use these to regress appropriateness ratings, effectively automating rating for suitability. The results suggest that certain topics inferred may be useful in detecting latent inappropriateness -- yielding recall up to 96% and low regression errors.

Published
2016
Full Text
View/download PDF

268. An Adaptive Psychoacoustic Model for Automatic Speech Recognition

Author

Dai, Peng, Teng, Xue, Rudzicz, Frank, and Soon, Ing Yann

Subjects
FOS: Computer and information sciences, Sound (cs.SD), Computer Science - Computation and Language, Computation and Language (cs.CL), Computer Science - Sound
Abstract

Compared with automatic speech recognition (ASR), the human auditory system is more adept at handling noise-adverse situations, including environmental noise and channel distortion. To mimic this adeptness, auditory models have been widely incorporated in ASR systems to improve their robustness. This paper proposes a novel auditory model which incorporates psychoacoustics and otoacoustic emissions (OAEs) into ASR. In particular, we successfully implement the frequency-dependent property of psychoacoustic models and effectively improve resulting system performance. We also present a novel double-transform spectrum-analysis technique, which can qualitatively predict ASR performance for different noise types. Detailed theoretical analysis is provided to show the effectiveness of the proposed algorithm. Experiments are carried out on the AURORA2 database and show that the word recognition rate using our proposed feature extraction method is significantly increased over the baseline. Given models trained with clean speech, our proposed method achieves up to 85.39% word recognition accuracy on noisy data.

Published
2016
Full Text
View/download PDF

270. Reality recalled: Elders, memory and VR

Author

Ladly, Martha J, primary, Bakker, Thoreau, additional, Chadha, Kartikay, additional, Farrelly, Glen, additional, Micak, Katie, additional, Penn, Gerald, additional, and Rudzicz, Frank, additional

Published
2017
Full Text
View/download PDF

272. [P1-295]: EARLY DETECTION OF COGNITIVE DISORDERS SUCH AS DEMENTIA ON THE BASIS OF SPEECH ANALYSIS: A CROSS-LINGUISTIC COMPARISON OF SPEECH FEATURES

Author

Konig, Alexandra, primary, Rudzicz, Frank, additional, Fraser, Kathleen C., additional, Kaufman, Liam, additional, Alexandersson, Jan, additional, Linz, Nicklas, additional, Tröger, Johannes, additional, Wolters, Maria, additional, Bremond, Francois, additional, and Robert, Philippe, additional

Published
2017
Full Text
View/download PDF

276. Designing Speech, Acoustic and Multimodal Interactions

Author

Munteanu, Cosmin, primary, Irani, Pourang, additional, Oviatt, Sharon, additional, Aylett, Matthew, additional, Penn, Gerald, additional, Pan, Shimei, additional, Sharma, Nikhil, additional, Rudzicz, Frank, additional, Gomez, Randy, additional, Cowan, Ben, additional, and Nakamura, Keisuke, additional

Published
2017
Full Text
View/download PDF

278. On the impact of non-modal phonation on phonological features

Author

Cernak, Milos, primary, Noth, Elmar, additional, Rudzicz, Frank, additional, Christensen, Heidi, additional, Orozco-Arroyave, Juan Rafael, additional, Arora, Raman, additional, Bocklet, Tobias, additional, Chinaei, Hamidreza, additional, Hannink, Julius, additional, Nidadavolu, Phani Sankar, additional, Vasquez, Juan Camilo, additional, Yancheva, Maria, additional, Vann, Alyssa, additional, and Vogler, Nikolai, additional

Published
2017
Full Text
View/download PDF

280. SLPAT 2015: 6th Workshop on Speech and Language Processing for Assistive Technologies

Author

Alexandersson, Jan, Ercan, Altinsoy, Christensen, Heidi, Ljunglöf, Peter, Portet, François, Rudzicz, Frank, Deutsches Forschungszentrum für Künstliche Intelligenz GmbH = German Research Center for Artificial Intelligence (DFKI), Technische Universität Dresden = Dresden University of Technology (TU Dresden), Department of Computer Sciences [Scheffield], University of Sheffield [Sheffield], University of Gothenburg (GU), Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole (GETALP), Laboratoire d'Informatique de Grenoble (LIG), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-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 )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), University of Toronto, Toronto Rehabilitation Institute [Toronto], and University Health Network

Subjects
ComputingMilieux_MISCELLANEOUS, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

International audience

Published
2015

281. Learning measures of semi-additive behaviour

Author

Chinaei, Hamidreza, Rais-Ghasem, Mohsen, and Rudzicz, Frank

Subjects
FOS: Computer and information sciences, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence
Abstract

In business analytics, measure values, such as sales numbers or volumes of cargo transported, are often summed along values of one or more corresponding categories, such as time or shipping container. However, not every measure should be added by default (e.g., one might more typically want a mean over the heights of a set of people); similarly, some measures should only be summed within certain constraints (e.g., population measures need not be summed over years). In systems such as Watson Analytics, the exact additive behaviour of a measure is often determined by a human expert. In this work, we propose a small set of features for this issue. We use these features in a case-based reasoning approach, where the system suggests an aggregation behaviour, with 86% accuracy in our collected dataset., Comment: 7 pages, 11 figures, 5 tables

Published
2015
Full Text
View/download PDF

282. Context is not key: Detecting Alzheimer’s disease with both classical and transformer-based neural language models

Author

TaghiBeyglou, Behrad and Rudzicz, Frank

Abstract

Natural language processing (NLP) has exhibited potential in detecting Alzheimer’s disease (AD) and related dementias, particularly due to the impact of AD on spontaneous speech. Recent research has emphasized the significance of context-based models, such as Bidirectional Encoder Representations from Transformers (BERT). However, these models often come at the expense of increased complexity and computational requirements, which are not always accessible. In light of these considerations, we propose a straightforward and efficient word2vec-based model for AD detection, and evaluate it on the Alzheimer’s Dementia Recognition through Spontaneous Speech (ADReSS) challenge dataset. Additionally, we explore the efficacy of fusing our model with classic linguistic features and compare this to other contextual models by fine-tuning BERT-based and Generative Pre-training Transformer (GPT) sequence classification models. We find that simpler models achieve a remarkable accuracy of 92% in classifying AD cases, along with a root mean square error of 4.21 in estimating Mini-Mental Status Examination (MMSE) scores. Notably, our models outperform all state-of-the-art models in the literature for classifying AD cases and estimating MMSE scores, including contextual language models.

Published
2024
Full Text
View/download PDF

283. Genetics providers’ perspectives on the use of digital tools in clinical practice

Author

Lee, Whiwon, Hirjikaka, Daena, Grewal, Sonya, Shaw, Angela, Luca, Stephanie, Clausen, Marc, Bombard, Yvonne, Hayeems, Robin Z., Bombard, Yvonne, Hayeems, Robin Z., Aronson, Melyssa, Bernier, Francois, Brudno, Michael, Carroll, June C., Chad, Lauren, Clausen, Marc, Cohn, Ronald, Costain, Gregory, Dhalla, Irfan, Faghfoury, Hanna, Friedman, Jan, Hewson, Stacy, Jamieson, Trevor, Jobling, Rebekah, Kodida, Rita, Laberge, Anne-Marie, Lerner-Ellis, Jordan, Liston, Eriskay, Luca, Stephanie, Mamdani, Muhammad, Marshall, Christian R., Osmond, Matthew, Pham, Quynh, Reble, Emma, Rudzicz, Frank, Seto, Emily, Shastri-Estrada, Serena, Shuman, Cheryl, Silver, Josh, Smith, Maureen, Thorpe, Kevin, and Ungar, Wendy J.

Abstract

Digital tools are increasingly incorporated into genetics practice to address challenges with the current model of care. Yet, genetics providers’ perspectives on digital tool use are not well characterized.

Published
2024
Full Text
View/download PDF

287. CloudCAST — Remote Speech Technology for Speech Professionals

Author

Green, Phil, primary, Marxer, Ricard, additional, Cunningham, Stuart, additional, Christensen, Heidi, additional, Rudzicz, Frank, additional, Yancheva, Maria, additional, Coy, André, additional, Malavasi, Massimiliano, additional, Desideri, Lorenzo, additional, and Tamburini, Fabio, additional

Published
2016
Full Text
View/download PDF

290. Poster

Author

Liaqat, Daniyal, primary, Thukral, Ishan, additional, Sin, Parco, additional, Alshaer, Hisham, additional, Rudzicz, Frank, additional, de Lara, Eyal, additional, Wu, Robert, additional, and Gershon, Andrea, additional

Published
2016
Full Text
View/download PDF

300. A novel approach for acoustic estimation of neck fluid volume between men and women.

Author

Shokrollahi, Mehrnaz, Rudzicz, Frank, Vena, Daniel, Bradley, T. Douglas, and Yadollahi, Azadeh

Subjects
*SLEEP apnea syndromes, *KALMAN filtering, *TRACHEA, *PHARYNX, *EDEMA
Abstract

Obstructive Sleep apnea can be caused by fluid shift from the legs to the neck that narrows the upper airway (UA) and contributes to changes in tracheal sound. Tracheal sound is generated from the turbulent airflow in the pharynx and respiratory airways and it has recently been used to estimate increases in neck fluid volume (NFV). However, tracheal sound is also highly variable among people, especially across the sexes. In this paper, a novel method is proposed to select tracheal sound features towards estimating NFV in men and women separately. To validate this method, it was applied to the tracheal sound data of 28 healthy individuals. Our proposed feature selection algorithm is based on sparse representations and incorporates NFV to maximize the relevance of selected features. This feature selection eliminates the dependence of the previous methods on calibrating the model for every individual. Two models, regression and Kalman filters, are then used to estimate NFV from selected features. Kalman filter obtains the highest performance, estimating NFV with more than 90% accuracy in both men and women. This algorithm can be used to develop non-invasive acoustic technologies to investigate the effects of fluid on UA anatomy in general applications. These results could be used to develop convenient devices to monitor the neck edema and its contribution to sleep apnea severity in fluid retaining patients such as heart or renal failure. [ABSTRACT FROM AUTHOR]

Published
2018
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results