Centre for Speech Technology Research

Research output

Research output per year 1995 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2023 2025

• 697 Conference contribution
• 139 Article
• 13 Chapter
• 12 Doctoral Thesis
• 40 More
  • 6 Paper
  • 5 Chapter (peer-reviewed)
  • 5 Working paper
  • 4 Book
  • 4 Other chapter contribution
  • 3 Poster
  • 2 Abstract
  • 2 Special issue
  • 2 Preprint
  • 1 Entry for encyclopedia/dictionary
  • 1 Foreword/postscript
  • 1 Other
  • 1 Editorial
  • 1 Literature review
  • 1 Digital or Visual Products
  • 1 Other contribution

Research output per year

Research output per year

Search results

• 2025

  Learning nonlinear dynamics in physical modelling synthesis using neural ordinary differential equations

  Zheleznov, V., Bilbao, S., Wright, A. & King, S., 6 May 2025, (Accepted/In press) Proceedings of the 28th International Conference on Digital Audio Effects (DAFx25). p. 1-8 8 p. (Proceedings of the International Conference on Digital Audio Effects).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Neural Network 100%
  • Network Architecture 100%
  • Machine Learning Approach 100%
  • Vibration Amplitude 100%
  • Applied Machine Learning 100%

• Synthesising a corpus of Gaelic traditional narrative with cross-lingual text expansion

  Lamb, W., Han, D., Klejch, O., Alex, B. & Bell, P., 24 Jan 2025, Proceedings of the 5th Celtic Language Technology Workshop. Abu Dhabi: ACL Anthology, p. 12–26 12 p.

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Language Modeling 100%
  • Text Expansion 100%
  • Low-resource Languages 100%
  • Multilingual LLM 100%
  • Sparsity 50%

• Advancing CTC models for better speech alignment: A topological approach

  Zhao, Z. & Bell, P., 16 Jan 2025, 2024 IEEE Spoken Language Technology Workshop (SLT). Singapore: Institute of Electrical and Electronics Engineers, p. 279-285 7 p. (Proceedings of the IEEE Spoken Language Technology Workshop).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Speech Recognition System 100%
  • Classification Models 100%
  • Automatic Speech Recognition 100%
  • Speech Discrimination 100%
  • Recognition Performance 50%

• Language bias in self-supervised learning for automatic speech recognition

  Storey, E., Harte, N. & Bell, P., 16 Jan 2025, Proceedings of the 2024 IEEE Spoken Language Technology Workshop. Singapore: Institute of Electrical and Electronics Engineers, p. 37-42 6 p. (Proceedings of the IEEE Spoken Language Technology Workshop).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Speech Recognition 100%
  • Self-Supervised Learning 100%
  • Subnetwork 40%
  • Training Data 40%
  • Large Data Set 20%
• 2024

  Characterizing code-switching: Applying linguistic principles for metric assessment and development

  Chi, J., Wallington, E. & Bell, P., 5 Sept 2024, Proceedings of Interspeech 2024. Lapidot, I. & Gannot, S. (eds.). ISCA, p. 7-11 5 p. (Proceedings of Interspeech).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Metrics 100%
  • Code-switching 100%
  • Linguistics 100%
  • Translation System 100%
  • Machine Translation 100%

• An initial investigation of language adaptation for TTS systems under low-resource scenarios

  Gong, C., Cooper, E., Wang, X., Qiang, C., Geng, M., Wells, D., Wang, L., Dang, J., Tessier, M., Pine, A., Richmond, K. & Yamagishi, J., 1 Sept 2024, Interspeech 2024. International Speech Communication Association (ISCA), p. 1-5 5 p. (Interspeech).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Target Language 100%
  • Language Identification 50%
  • Self-Supervised Learning 50%
  • Self-Supervised Representation Learning 50%
  • Low-resource Languages 50%

• Experimental evaluation of MOS, AB and BWS listening test designs

  Wells, D., Aldana Blanco, A. L., Valentini-Botinhao, C., Cooper, E., Pine, A., Yamagishi, J. & Richmond, K., 1 Sept 2024, Interspeech 2024. International Speech Communication Association (ISCA), p. 1-5 5 p. (Interspeech).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Speech 100%

• Learning pronunciation from other accents via pronunciation knowledge transfer

  Sun, S. & Richmond, K., 1 Sept 2024, Interspeech 2024. International Speech Communication Association (ISCA), p. 1-5 5 p. (Interspeech).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Lexical 100%
  • Knowledge Transfer 100%
  • Linguistics 50%
  • English accents 50%

• Low-dimensional style token control for hyperarticulated speech synthesis

  Nishihara, M., Wells, D., Richmond, K. & Pine, A., 1 Sept 2024, Interspeech 2024. International Speech Communication Association (ISCA), p. 1-5 5 p. (Interspeech).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Speech Synthesis 100%
  • tokens 100%
  • Principal Component Analysis 100%
  • Corpus 20%
  • plosives 20%

• Analyzing the role of part-of-speech in code-switching: A corpus-based study

  Chi, J. & Bell, P., 22 Mar 2024, Findings of the Association for Computational Linguistics: EACL 2024. Graham, Y. & Purver, M. (eds.). Association for Computational Linguistics, p. 1712–1721 10 p.

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Part of speech 100%
  • Code-switching 100%
  • Corpus-based study 100%
  • Cognitive Process 100%
  • Speaker 14%

• BOOTSTRAP PREDICTIVE CODING: INVESTIGATING A NON-CONTRASTIVE SELF-SUPERVISED LEARNING APPROACH

  Mohamied, Y. & Bell, P., 18 Mar 2024, ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, p. 11541-11545 5 p. (International Conference on Acoustics, Speech, and Signal Processing (ICASSP)).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Causal Model 100%
  • Masking 100%

• CAN WE TRUST EXPLAINABLE AI METHODS ON ASR? AN EVALUATION ON PHONEME RECOGNITION

  Wu, X., Bell, P. & Rajan, A., 18 Mar 2024, ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, p. 10296-10300 5 p. (International Conference on Acoustics, Speech, and Signal Processing (ICASSP)).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Image Classification 100%
  • Speech Recognition 100%
  • Artificial Intelligence 100%
  • Phoneme 100%
  • Explainable Artificial Intelligence 100%

• Cultivating Spoken Language Technologies for Unwritten Languages

  Reitmaier, T., Kalarikalayil Raju, D., Klejch, O., Wallington, E., Markl, N., Pearson, J., Jones, M., Bell, P. & Robinson, S., 9 Mar 2024, (Accepted/In press) CHI '24: Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems. ACM, p. 1-17

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Spoken Language 100%
  • Annotation 66%
  • Information Retrieval Systems 66%
  • Use Case 33%
  • Natural Language Processing 33%

• Invert-Classify: Recovering Discrete Prosody Inputs for Text-To-Speech

  Sanders, N. & Richmond, K., 19 Jan 2024, 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Institute of Electrical and Electronics Engineers, p. 1-7 7 p. 10389773

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Text To Speech 100%
  • Annotation 25%
  • Training Data 25%

• Hierarchical intonation modelling for speech synthesis using Legendre polynomial coefficients

  O'Mahony, J., Corkey, N., Lai, C., Klabbers, E. & King, S., 2024, Proceedings of Speech Prosody 2024. Chen, Y., Chen, A. & Arvaniti, A. (eds.). International Speech Communication Association (ISCA), p. 1030-1034 5 p. (Speech Prosody).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Speech Synthesis 100%
  • Legendre Polynomial 100%
  • Synthetic Speech Quality 33%
  • Synthesis Model 33%
  • High Correlation 33%

• Is there an uncanny valley for speech? Investigating listeners’ evaluations of realistic synthesised voices

  Ross, A., Corley, M. & Lai, C., 2024, Proceedings of Speech Prosody 2024. Chen, Y., Chen, A. & Arvaniti, A. (eds.). International Speech Communication Association (ISCA), p. 1115-1119 5 p. (Speech Prosody).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Uncanny 100%
  • Likeness 50%
  • Speaker 25%
  • Online 25%
  • Pleasantness 25%
• 2023

  Differentiable grey-box modelling of phaser effects using frame-based spectral processing

  Carson, A., King, S., Valentini Botinhao, C. & Bilbao, S., 4 Sept 2023, Proceedings of the 26th International Conference on Digital Audio Effects. Copenhagen, p. 1-8 8 p. (Proceedings of the International Conference on Digital Audio Effects).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Spectral Processing 100%
  • Control Signal 100%
  • Frequency Domain 50%
  • Transients 50%
  • Significant Change 50%

• A low-resource pipeline for text-to-speech from found data with application to Scottish Gaelic

  Wells, D., Richmond, K. & Lamb, W., Sept 2023, Proceedings of the Annual Conference of the International Speech Communication Association: Interspeech 2023. Harte, N., Carson-Berndsen, J. & Jones, G. (eds.). Dublin: ISCA, p. 4324-4328 (Interspeech - Annual Conference of the International Speech Communication Association).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Text To Speech 100%
  • Speech Sound 100%
  • Speech Synthesis System 50%
  • Small Data Set 50%
  • speech corpus 50%

• Everyone has an accent

  Markl, N. & Lai, C., Sept 2023, Proceedings of the Annual Conference of the International Speech Communication Association: Interspeech 2023. Harte, N., Carson-Berndsen, J. & Jones, G. (eds.). Dublin: ISCA, p. 4424-4427 (Interspeech - Annual Conference of the International Speech Communication Association).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Published Research 100%
  • Disciplinary Difference 100%
  • Logopedics 100%
  • Speech Technology 100%

• Intonation control for neural text-to-speech synthesis with polynomial models of F0

  Corkey, N., O'Mahony, J. & King, S., Sept 2023, Proceedings of the Annual Conference of the International Speech Communication Association: Interspeech 2023. Harte, N., Carson-Berndsen, J. & Jones, G. (eds.). Dublin: ISCA, p. 2014-2015 2 p. (Interspeech - Annual Conference of the International Speech Communication Association).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Speech Synthesis 100%
  • Human-in-the-Loop 100%
  • Text To Speech 100%
  • Legendre Polynomial 100%
  • Polynomial Model 100%

• Silent speech recognition with articulator positions estimated from tongue ultrasound and lip video

  Beeson, R. & Richmond, K., Sept 2023, Proceedings of the Annual Conference of the International Speech Communication Association: Interspeech 2023. Harte, N., Carson-Berndsen, J. & Jones, G. (eds.). Dublin: ISCA, p. 1149-1153 (Interspeech - Annual Conference of the International Speech Communication Association).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Speech Recognition System 100%
  • Speech Recognition 100%
  • Estimated Position 100%
  • Pose Estimation 100%

• Synthesis after a couple PINTs: Investigating the role of pause-internal phonetic particles in speech synthesis and perception

  Elmers, M., O'Mahony, J. & Székely, É., Sept 2023, Proceedings of the Annual Conference of the International Speech Communication Association: Interspeech 2023. Harte, N., Carson-Berndsen, J. & Jones, G. (eds.). Dublin: ISCA, p. 4843-4847 5 p. (Interspeech - Annual Conference of the International Speech Communication Association).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Pause 100%
  • Speech Synthesis 100%
  • Speech Perception 100%
  • Material Particle 100%
  • Speaker 7%

• Synthesising turn-taking cues using natural conversational data

  O'Mahony, J., Lai, C. & King, S., 28 Aug 2023, Proceedings of the 12th ISCA Speech Synthesis Workshop: (SSW2023). Bailly, G., Hueber, T., Lolive, D., Obin , N. & Perrotin, O. (eds.). Grenoble: ISCA, p. 75-80 5 p. (Proceedings of the ISCA Workshop).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Speech Synthesis 100%
  • Context Dependent 50%
  • Synthesis Model 50%
  • Objective Measure 50%
  • Subjective Evaluation 50%

• ASR and Emotional Speech: A Word-Level Investigation of the Mutual Impact of Speech and Emotion Recognition

  Li, Y., Zhao, Z., Klejch, O., Bell, P. & Lai, C., 20 Aug 2023, Proc. INTERSPEECH 2023. International Speech Communication Association, p. 1449-1453 5 p. (Interspeech).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Speech Recognition 100%
  • Emotion Recognition 100%
  • Automatic Speech Recognition 100%
  • Error Rate 100%
  • Emotions 18%

• Capturing Formality in Speech Across Domains and Languages

  Bhattacharya, D., Chi, J., Hirschberg, J. & Bell, P., 20 Aug 2023, Proc. INTERSPEECH 2023. International Speech Communication Association, p. 1030-1034 5 p. (Interspeech).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Initial Expectation 100%
  • speech corpus 100%
  • Written Language 100%
  • Spoken Language 100%
  • Concludes 100%

• Evaluating and reducing the distance between synthetic and real speech distributions

  Minixhofer, C., Klejch, O. & Bell, P., 20 Aug 2023, Proc. INTERSPEECH 2023. International Speech Communication Association, p. 2078-2082 5 p. (Interspeech).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Speech Recognition 100%
  • Speech Discrimination 100%
  • Speech Recognition System 50%
  • Neural Network Architecture 50%
  • Neural Network 33%

• Quantifying the perceptual value of lexical and non-lexical channels in speech

  Wallbridge, S., Bell, P. & Lai, C., 20 Aug 2023, Proc. INTERSPEECH 2023. International Speech Communication Association, p. 2708-2712 5 p. (Interspeech).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Lexical 100%
  • Dialogue Form 33%

• Regarding Topology and Variant Frame Rates for Differentiable WFST-based End-to-End ASR

  Zhao, Z. & Bell, P., 20 Aug 2023, Proc. INTERSPEECH 2023. International Speech Communication Association, p. 4903-4907 5 p. (Interspeech).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Speech Recognition 100%
  • Speech Discrimination 100%
  • Speech Recognition System 33%
  • Neural Network Architecture 33%

• Transfer Learning for Personality Perception via Speech Emotion Recognition

  Li, Y., Bell, P. & Lai, C., 20 Aug 2023, Proc. INTERSPEECH 2023. International Speech Communication Association, p. 5197-5201 5 p. (Interspeech).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Learning Transfer 100%

• Unsupervised Code-switched Text Generation from Parallel Text

  Chi, J., Lu, B., Eisner, J., Bell, P., Jyothi, P. & Ali, A. M., 20 Aug 2023, Proc. INTERSPEECH 2023. International Speech Communication Association, p. 1419-1423 5 p. (Interspeech).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Lexical 100%
  • Parallel texts 100%
  • text generation 100%
  • Lexical Information 100%
  • Entropy Reduction 50%

• Automatic transcription and (de)standardisation

  Markl, N., Wallington, E., Klejch, O., Reitmaier, T., Bailey, G., Pearson, J., Jones, M., Robinson, S. & Bell, P., 18 Aug 2023, Proceedings - SIGUL 2023, 2nd Annual Meeting of the Special Interest Group on Under-resourced Languages: A Satellite Workshop of Interspeech 2023. International Speech Communication Association, p. 93-97 5 p.

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Language use 100%
  • Writing practices 50%
  • IsiXhosa 50%

• Investigating the relationship between prosodic entrainment and interaction style

  Kruyt, J., Huttner, L.-M. & O'Mahony, J., 10 Aug 2023, Proceedings of the 20th International Congress of Phonetic Sciences. Skarnitzl, R. & Volín, J. (eds.). Prague: Guarant International, p. 3492-3496 514

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Turn-Taking 100%

• Language redundancy effects on F0: A preliminary controlled study

  Zhang, C., Lai, C., Napoleao de Souza, R., Turk, A. & Bögel, T., 10 Aug 2023, Proceedings of the 20th International Congress of Phonetic Sciences. Skarnitzl, R. & Volín, J. (eds.). Prague: Guarant International, p. 1593-1597 877

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Controlled 100%
  • Fundamental Frequency 100%
  • Adjectives 100%
  • Salience 100%
  • Familiarity 100%

• What does BERT learn about prosody?

  Kakouros, S. & O'Mahony, J., 10 Aug 2023, Proceedings of the 20th International Congress of Phonetic Sciences. Skarnitzl, R. & Volín, J. (eds.). Prague: Guarant International, p. 1454-1458 622

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Bidirectional Encoder Representations From Transformers 100%
  • Language Modeling 33%
  • Syntactics 33%
  • Interpretability 33%
  • Language Processing 33%

• Do prosody transfer models transfer prosody?

  Sigurgeirsson, A. T. & King, S., Jun 2023, ICASSP 2023: 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; vol. 2023-June).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Speech Synthesis 100%
  • Synthetic Speech 100%
  • Level Representation 100%
  • Speech Generation 100%
  • Text To Speech 100%

• Autovocoder: fast waveform generation from a learned speech representation using differentiable digital signal processing

  Webber, J., Valentini Botinhao, C., Williams, E., Eje Henter, G. & King, S., 5 May 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, 5 p. (International Conference on Acoustics, Speech, and Signal Processing (ICASSP)).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Digital Signal Processing 100%
  • Machine Learning 100%
  • Learning System 100%
  • Spectrogram 100%
  • Intermediate Representation 50%

• Efficient intelligibility evaluation using keyword spotting: A study on audio-visual speech enhancement

  Valentini Botinhao, C., Aldana Blanco, A. L., Klejch, O. & Bell, P., 5 May 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, 5 p. (International Conference on Acoustics, Speech, and Signal Processing (ICASSP)).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Speech Enhancement 100%
  • Case Study 100%
  • Language Modeling 100%
  • Visual Stimuli 50%

• Explanations for automatic speech recognition

  Wu, X., Bell, P. & Rajan, A., 5 May 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, 5 p. (International Conference on Acoustics, Speech, and Signal Processing (ICASSP)).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Speech Recognition 100%
  • Explainable Artificial Intelligence 100%
  • Image Classification 100%
  • Machine Learning 100%
  • Artificial Intelligence 100%

• Multimodal Dyadic Impression Recognition via Listener Adaptive Cross-Domain Fusion

  Li, Y., Bell, P. & Lai, C., 5 May 2023, 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, 5 p. (International Conference on Acoustics, Speech, and Signal Processing (ICASSP)).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Spoken Dialog System 100%
  • Affective Computing 100%

• Puffin: pitch-synchronous neural waveform generation for fullband speech on modest devices

  Watts, O., Wihlborg, L. & Valentini Botinhao, C., 5 May 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, 5 p. (International Conference on Acoustics, Speech, and Signal Processing (ICASSP)).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Synthetic Speech Quality 100%
  • System Complexity 100%
  • Reduce Complexity 100%
  • Communication Device 100%
  • Time Fourier Transform 100%

• The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR

  Sanabria, R., Bogoychev, N., Markl, N., Carmantini, A., Klejch, O. & Bell, P., 5 May 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, p. 1-5 5 p.

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Edinburgh 100%
  • Corpus 100%
  • Automatic Speech Recognition 100%
  • varieties of English 100%
  • Democratization 100%

• Do dialogue representations align with perception? An empirical study

  Wallbridge, S., Bell, P. & Lai, C., 2 May 2023, Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics (ACL), Vol. 198. p. 2696–2713 (ACL proceedings).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Language Comprehension 100%
  • Plausibility 100%
  • Selection Task 100%
  • Autoregressive Model 100%
  • Human Performance 100%

• I Know Your Feelings Before You Do: Predicting Future Affective Reactions in Human-Computer Dialogue

  Li, Y., Inoue, K., Tian, L., Fu, C., Ishi, C., Ishiguro, H., Kawahara, T. & Lai, C., 19 Apr 2023, The ACM CHI Conference on Human Factors in Computing Systems. ACM Association for Computing Machinery, p. 1-7 8 p. 166

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Spoken Dialog System 100%
  • Computer Dialog 100%
  • Synchronicity 100%
  • Temporal Relationship 33%
  • Causal Relationship 33%

• Situating Automatic Speech Recognition Development within Communities of Under-heard Language Speakers

  Reitmaier, T., Wallington, E., Klejch, O., Markl, N., Lam-Yee-Mui, L.-M., Pearson, J., Jones, M., Bell, P. & Robinson, S., 19 Apr 2023, CHI '23: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems. New York: ACM, p. 1-17 17 p. 406

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Language Speaker 100%
  • Speech Recognition 100%
  • Human-Computer Interaction 20%
  • Community Member 20%
  • Mobile App 20%

• AVSE Challenge: Audio-Visual Speech Enhancement Challenge

  Aldana Blanco, A. L., Valentini Botinhao, C., Klejch, O., Gogate, M., Dashtipour, K., Hussain, A. & Bell, P., 27 Jan 2023, Proceedings of the 2022 IEEE Spoken Language Technology Workshop. Institute of Electrical and Electronics Engineers, p. 465-471 7 p.

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Speech Enhancement 100%
  • Human Participant 12%
  • noise signal 12%

• Exploration of A Self-Supervised Speech Model: A Study on Emotional Corpora

  Li, Y., Mohamied, Y., Bell, P. & Lai, C., 27 Jan 2023, Proceedings of the 2022 IEEE Spoken Language Technology Workshop. Institute of Electrical and Electronics Engineers, p. 868-875 8 p.

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Theoretical Basis 100%
  • Word Recognition 100%
• 2022

  Improving code-switched ASR with linguistic information

  Chi, J. & Bell, P., 3 Nov 2022, Proceedings of the 29th International Conference on Computational Linguistics. Calzolari, N., Huang, C.-R., Kim, H., Pustejovsky, J., Wanner, L., Choi, K.-S., Ryu, P.-M., Chen, H.-H., Donatelli, L., Ji, H., Kurohashi, S., Paggio, P., Xue, N., Kim, S., Hahm, Y., He, Z., Lee, T. K., Santus, E., Bond, F. & Na, S.-H. (eds.). ACL Anthology, Vol. 29. p. 7171-7176 6 p. (COLING; vol. 29, no. 1).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Automatic Speech Recognition 100%
  • Linguistics 100%
  • Code-switching 80%
  • Constraint Part 25%
  • Bi-lingual speakers 20%

• Back to the future: Extending the Blizzard Challenge 2013

  Le Maguer, S., King, S. & Harte, N., 22 Sept 2022, Proceedings of Interspeech 2022. Ko, H. & Hansen, J. H. L. (eds.). ISCA, p. 2378-2382 (Interspeech - Annual Conference of the International Speech Communication Association).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  • Modern Technology 100%
  • Deep Learning Method 100%
  • Mean Opinion Score 100%
  • Neural Vocoder 100%
  • Speech Synthesis 50%

• Combining conversational speech with read speech to improve prosody in Text-to-Speech synthesis

  O'Mahony, J., Lai, C. & King, S., 22 Sept 2022, Proceedings of Interspeech 2022. Ko, H. & Hansen, J. H. L. (eds.). ISCA, p. 3388-3392 ( Interspeech - Annual Conference of the International Speech Communication Association).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Speech Synthesis 100%
  • Text To Speech 100%
  • Sequence Model 33%
  • Seq2Seq 33%

• Predicting pairwise preferences between TTS audio stimuli using parallel ratings data and anti-symmetric twin neural networks

  Valentini-Botinhao, C., Ribeiro, M. S., Watts, O., Richmond, K. & Eje Henter, G., 22 Sept 2022, Proceedings of Interspeech 2022. Ko, H. & Hansen, J. H. L. (eds.). ISCA, p. 471-475 5 p.

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  File

  • Neural Network 100%
  • Pairwise Preference 100%
  • Trained Neural Network 50%
  • Subjective Preference 50%
  • Training Set 50%