Search

Your search keyword '"Carson-Berndsen, Julie"' showing total 227 results
Start Over Author "Carson-Berndsen, Julie"

Refine your results

more »

more »

more »

more »
227 results on '"Carson-Berndsen, Julie"'

1. Real-Time Textless Dialogue Generation

Author

Mai, Long and Carson-Berndsen, Julie

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

Recent advancements in large language models (LLMs) have led to significant progress in text-based dialogue systems. These systems can now generate high-quality responses that are accurate and coherent across a wide range of topics and tasks. However, spoken dialogue systems still lag behind in terms of naturalness. They tend to produce robotic interactions, with issues such as slow response times, overly generic or cautious replies, and a lack of natural rhythm and fluid turn-taking. This shortcoming is largely due to the over-reliance on the traditional cascaded design, which involve separate, sequential components, as well as the use of text as an intermediate representation. This paper propose a real-time, textless spoken dialogue generation model (RTTL-DG) that aims to overcome these challenges. Our system enables fluid turn-taking and generates responses with minimal delay by processing streaming spoken conversation directly. Additionally, our model incorporates backchannels, filters, laughter, and other paralinguistic signals, which are often absent in cascaded dialogue systems, to create more natural and human-like interactions. The implementations and generated samples are available in our repository: https://github.com/mailong25/rts2s-dg

Published
2025

2. Improving Linguistic Diversity of Large Language Models with Possibility Exploration Fine-Tuning

Author

Mai, Long and Carson-Berndsen, Julie

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

While Large Language Models (LLMs) have made significant strides in replicating human-like abilities, there are concerns about a reduction in the linguistic diversity of their outputs. This results in the homogenization of viewpoints and perspectives, as well as the underrepresentation of specific demographic groups. Although several fine-tuning and prompting techniques have been suggested to tackle the issue, they are often tailored to specific tasks or come with a substantial increase in computational cost and latency. This makes them challenging to apply to applications that demand very low latency, such as chatbots and virtual assistants. We propose Possibility Exploration Fine-Tuning (PEFT), a task-agnostic framework that enhances the text diversity of LLMs without increasing latency or computational cost. Given the same prompt, models fine-tuned with PEFT can simultaneously generate multiple diverse responses, each corresponding with a controllable possibility number. Experiments on dialogue and story generation tasks demonstrate that PEFT significantly enhances the diversity of LLM outputs, as evidenced by lower similarity between candidate responses. Since PEFT emphasizes semantic diversity over lexical diversity, it can also notably reduce demographic bias in dialogue systems. The implementations and datasets are available in our repository: https://github.com/mailong25/peft_diversity

Published
2024

3. Enhancing conversational quality in language learning chatbots: An evaluation of GPT4 for ASR error correction

Author

Mai, Long and Carson-Berndsen, Julie

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

The integration of natural language processing (NLP) technologies into educational applications has shown promising results, particularly in the language learning domain. Recently, many spoken open-domain chatbots have been used as speaking partners, helping language learners improve their language skills. However, one of the significant challenges is the high word-error-rate (WER) when recognizing non-native/non-fluent speech, which interrupts conversation flow and leads to disappointment for learners. This paper explores the use of GPT4 for ASR error correction in conversational settings. In addition to WER, we propose to use semantic textual similarity (STS) and next response sensibility (NRS) metrics to evaluate the impact of error correction models on the quality of the conversation. We find that transcriptions corrected by GPT4 lead to higher conversation quality, despite an increase in WER. GPT4 also outperforms standard error correction methods without the need for in-domain training data.

Published
2023

4. Investigating the Sensitivity of Automatic Speech Recognition Systems to Phonetic Variation in L2 Englishes

Author

O'Neill, Emma and Carson-Berndsen, Julie

Subjects
Computer Science - Computation and Language, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

Automatic Speech Recognition (ASR) systems exhibit the best performance on speech that is similar to that on which it was trained. As such, underrepresented varieties including regional dialects, minority-speakers, and low-resource languages, see much higher word error rates (WERs) than those varieties seen as 'prestigious', 'mainstream', or 'standard'. This can act as a barrier to incorporating ASR technology into the annotation process for large-scale linguistic research since the manual correction of the erroneous automated transcripts can be just as time and resource consuming as manual transcriptions. A deeper understanding of the behaviour of an ASR system is thus beneficial from a speech technology standpoint, in terms of improving ASR accuracy, and from an annotation standpoint, where knowing the likely errors made by an ASR system can aid in this manual correction. This work demonstrates a method of probing an ASR system to discover how it handles phonetic variation across a number of L2 Englishes. Specifically, how particular phonetic realisations which were rare or absent in the system's training data can lead to phoneme level misrecognitions and contribute to higher WERs. It is demonstrated that the behaviour of the ASR is systematic and consistent across speakers with similar spoken varieties (in this case the same L1) and phoneme substitution errors are typically in agreement with human annotators. By identifying problematic productions specific weaknesses can be addressed by sourcing such realisations for training and fine-tuning thus making the system more robust to pronunciation variation.

Published
2023

5. Unsupervised domain adaptation for speech recognition with unsupervised error correction

Author

Mai, Long and Carson-Berndsen, Julie

Subjects
Computer Science - Sound, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

The transcription quality of automatic speech recognition (ASR) systems degrades significantly when transcribing audios coming from unseen domains. We propose an unsupervised error correction method for unsupervised ASR domain adaption, aiming to recover transcription errors caused by domain mismatch. Unlike existing correction methods that rely on transcribed audios for training, our approach requires only unlabeled data of the target domains in which a pseudo-labeling technique is applied to generate correction training samples. To reduce over-fitting to the pseudo data, we also propose an encoder-decoder correction model that can take into account additional information such as dialogue context and acoustic features. Experiment results show that our method obtains a significant word error rate (WER) reduction over non-adapted ASR systems. The correction model can also be applied on top of other adaptation approaches to bring an additional improvement of 10% relatively., Comment: Interspeech 2022

Published
2022

7. S-Capade: Spelling Correction Aimed at Particularly Deviant Errors

Author

O’Neill, Emma, Young, Robert, Thiaville, Elsa, MacCarthy, Muireann, Carson-Berndsen, Julie, Ventresque, Anthony, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Espinosa-Anke, Luis, editor, Martín-Vide, Carlos, editor, and Spasić, Irena, editor

Published
2020
Full Text
View/download PDF

12. Phoneme Recognition Using Acoustic Events

Author

Huebener, Kai and Carson-Berndsen, Julie

Subjects
Computer Science - Computation and Language
Abstract

This paper presents a new approach to phoneme recognition using nonsequential sub--phoneme units. These units are called acoustic events and are phonologically meaningful as well as recognizable from speech signals. Acoustic events form a phonologically incomplete representation as compared to distinctive features. This problem may partly be overcome by incorporating phonological constraints. Currently, 24 binary events describing manner and place of articulation, vowel quality and voicing are used to recognize all German phonemes. Phoneme recognition in this paradigm consists of two steps: After the acoustic events have been determined from the speech signal, a phonological parser is used to generate syllable and phoneme hypotheses from the event lattice. Results obtained on a speaker--dependent corpus are presented., Comment: 4 pages, to appear at ICSLP'94, PostScript version (compressed and uuencoded)

Published
1994

14. Towards a Better Representation of the Envelope Modulation of Aspiration Noise

Author

Cabral, João P., Carson-Berndsen, Julie, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Drugman, Thomas, editor, and Dutoit, Thierry, editor

Published
2013
Full Text
View/download PDF

15. LIMA: A Spoken Language Identification Framework

Author

Zahra, Amalia, Carson-Berndsen, Julie, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Železný, Miloš, editor, Habernal, Ivan, editor, and Ronzhin, Andrey, editor

Published
2013
Full Text
View/download PDF

16. Multiple Source Phoneme Recognition Aided by Articulatory Features

Author

Kane, Mark, Carson-Berndsen, Julie, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Mehrotra, Kishan G., editor, Mohan, Chilukuri K., editor, Oh, Jae C., editor, Varshney, Pramod K., editor, and Ali, Moonis, editor

Published
2011
Full Text
View/download PDF

17. Automatic Identification of Phonetic Similarity Based on Underspecification

Author

Kane, Mark, Mauclair, Julie, Carson-Berndsen, Julie, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, and Vetulani, Zygmunt, editor

Published
2011
Full Text
View/download PDF

18. The Corpus Analysis Toolkit - Analysing Multilevel Annotations

Author

Wilson, Stephen, Carson-Berndsen, Julie, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, and Vetulani, Zygmunt, editor

Published
2011
Full Text
View/download PDF

19. Automatic Rule Extraction for Modeling Pronunciation Variation

Author

Ahmed, Zeeshan, Carson-Berndsen, Julie, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, and Gelbukh, Alexander, editor

Published
2011
Full Text
View/download PDF

24. Evaluation

Author

Carson-Berndsen, Julie, Ide, Nancy, editor, Véronis, Jean, editor, and Carson-Berndsen, Julie

Published
1998
Full Text
View/download PDF

25. Silpa

Author

Carson-Berndsen, Julie, Ide, Nancy, editor, Véronis, Jean, editor, and Carson-Berndsen, Julie

Published
1998
Full Text
View/download PDF

29. Introduction

Author

Carson-Berndsen, Julie, Ide, Nancy, editor, Véronis, Jean, editor, and Carson-Berndsen, Julie

Published
1998
Full Text
View/download PDF

31. Conclusion

Author

Carson-Berndsen, Julie, Ide, Nancy, editor, Véronis, Jean, editor, and Carson-Berndsen, Julie

Published
1998
Full Text
View/download PDF

33. Phonetic Question Generation Using Misrecognition

Author

Kanokphara, Supphanat, Carson-Berndsen, Julie, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Carbonell, Jaime G., editor, Siekmann, Jörg, editor, Sojka, Petr, editor, Kopeček, Ivan, editor, and Pala, Karel, editor

Published
2006
Full Text
View/download PDF

34. Diagnostic Evaluation of Phonetic Feature Extraction Engines: A Case Study with the Time Map Model

Author

Aioanei, Daniel, Carson-Berndsen, Julie, Kanokphara, Supphanat, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Carbonell, Jaime G., editor, Siekmann, Jörg, editor, Ali, Moonis, editor, and Dapoigny, Richard, editor

Published
2006
Full Text
View/download PDF

35. Comparative Study: HMM and SVM for Automatic Articulatory Feature Extraction

Author

Kanokphara, Supphanat, Macek, Jan, Carson-Berndsen, Julie, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Carbonell, Jaime G., editor, Siekmann, Jörg, editor, Ali, Moonis, editor, and Dapoigny, Richard, editor

Published
2006
Full Text
View/download PDF

36. Phonetic Time Maps : Defining Constraints for Multilinear Speech Processing

Author

Carson-Berndsen, Julie, Walsh, Michael, Ide, Nancy, editor, Véronis, Jean, editor, Baayen, Harald, editor, Church, Kenneth W., editor, Klavans, Judith, editor, Barnard, David T., editor, Tufis, Dan, editor, Llisterri, Joaquim, editor, Johansson, Stig, editor, Mariani, Joseph, editor, Barry, William J., editor, and van Dommelen, Wim A., editor

Published
2005
Full Text
View/download PDF

39. Speaking Autonomous Intelligent Devices

Author

Ross, Robert J., McEleney, Bryan, Kelly, Robert, Abu-Amer, Tarek, Walsh, Michael, Carson-Berndsen, Julie, O’Hare, Gregory M. P., Goos, G., editor, Hartmanis, J., editor, van Leeuwen, J., editor, Carbonell, Jaime G., editor, Siekmann, Jörg, editor, O’Neill, Michael, editor, Sutcliffe, Richard F. E., editor, Ryan, Conor, editor, Eaton, Malachy, editor, and Griffith, Niall J. L., editor

Published
2002
Full Text
View/download PDF

42. Feature-Table-Based Automatic Question Generation for Tree-Based State Tying: A Practical Implementation

Author

Kanokphara, Supphanat, Carson-Berndsen, Julie, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Carbonell, Jaime G., editor, Siekmann, Jörg, editor, Ali, Moonis, editor, and Esposito, Floriana, editor

Published
2005
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results