Professor Jon Barker
PhD
School of Computer Science
Personal Chair
School Ethics Lead
Member of the Speech and Hearing (SpandH) research group
j.p.barker@sheffield.ac.uk
+44 114 222 1824
+44 114 222 1824
Regent Court (DCS)
Full contact details
Professor Jon Barker
School of Computer Science
Regent Court (DCS)
211 Portobello
Sheffield
S1 4DP
School of Computer Science
Regent Court (DCS)
211 Portobello
Sheffield
S1 4DP
- Profile
-
Professor Jon Barker is a member of the Speech and Hearing Research Group. He has a first degree in Electrical and Information Sciences from Cambridge University, UK. After receiving a PhD from the University of Sheffield in 1999, he worked for some time at GIPSA-lab, Grenoble and IDIAP research institute in Switzerland before returning to Sheffield where he has had a permanent post since 2002.
His research interests lie in noise-robust speech processing. Key application areas include distant-microphone speech recognition, speech intelligibility prediction and improved speech processing for hearing-aid users.
- Research interests
-
Professor Barker’s research interests are focused around machine listening and the computational modelling of human hearing. A recent focus has been on modelling speech intelligibility, ie can we predict whether or not a speech signal will be intelligible to a given listener?
This understanding will help us produce better signal processing for application such as hearing aids and cochlear implants. Another strand of his work is about taking insights gained from human auditory perception and using them to engineer robust automatic speech processing systems.
- Publications
-
Journal articles
- Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge. Computer Speech & Language, 89, 101685-101685.
- The Cadenza Woodwind Dataset: Synthesised Quartets for Music Information Retrieval and Machine Learning. Data in Brief, 111199-111199.
- Development of the 2nd Cadenza challenge for improving music listening for people with a hearing loss. The Journal of the Acoustical Society of America, 155(3_Supplement), A277-A277.
- Muddy, muddled, or muffled? Understanding the perception of audio quality in music by hearing aid users. Frontiers in Psychology, 15, 1310176.
- A systematic review of measurements of real-world interior car noise for the “Cadenza” machine-learning project. The Journal of the Acoustical Society of America, 153(3_supplement), A332-A332.
- Results of the second “clarity” enhancement challenge for hearing devices. The Journal of the Acoustical Society of America, 153(3_supplement), A48-A48.
- Dataset of British English speech recordings for psychoacoustics and speech processing research: The clarity speech corpus. Data in Brief, 41. View this article in WRRO
- Acoustic Modelling From Raw Source and Filter Components for Dysarthric Speech Recognition. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 30, 2968-2980.
- Launching the first “Clarity” Machine Learning Challenge to revolutionise hearing device processing. The Journal of the Acoustical Society of America, 148(4), 2711-2711.
- Lexical frequency effects in English and Spanish word misperceptions.. The Journal of the Acoustical Society of America, 145(2), EL136-EL141. View this article in WRRO
- A corpus of audio-visual Lombard speech with frontal and profile views. Journal of the Acoustical Society of America, 143(6), 523-529. View this article in WRRO
- The impact of the Lombard effect on audio and visual speech recognition systems. Speech Communication, 100, 58-68. View this article in WRRO
- The impact of automatic exaggeration of the visual articulatory features of a talker on the intelligibility of spectrally distorted speech. Speech Communication, 95, 127-136. View this article in WRRO
- An analysis of environment, microphone and data simulation mismatches in robust speech recognition. Computer Speech & Language, 46, 535-557. View this article in WRRO
- The third ‘CHiME’ speech separation and recognition challenge: Analysis and outcomes. Computer Speech and Language, 46, 605-626. View this article in WRRO
- Evaluation of scene analysis using real and simulated acoustic mixtures: Lessons learnt from the CHiME speech recognition challenges. The Journal of the Acoustical Society of America, 141(5), 3693-3693.
- Guest Editorial for the special issue on Multi-Microphone Speech Recognition in Everyday Environments. Computer Speech & Language. View this article in WRRO
- Spectral Reconstruction and Noise Model Estimation Based on a Masking Model for Noise Robust Speech Recognition. Circuits, Systems, and Signal Processing. View this article in WRRO
- A corpus of noise-induced word misperceptions for English.. Journal of the Acoustical Society of America, 140(5), EL458-EL463. View this article in WRRO
- An Overview, 137-172.
- The second 'CHiME' speech separation and recognition challenge: An overview of challenge systems and outcomes. 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013 - Proceedings, 162-167.
- MMSE-based missing-feature reconstruction with temporal modeling for robust speech recognition. IEEE Transactions on Audio, Speech and Language Processing, 21(3), 624-635.
- Speech spectral envelope enhancement by HMM-based analysis/resynthesis. IEEE Signal Processing Letters, 20(6), 563-566.
- A hearing-inspired approach for distant-microphone speech recognition in the presence of multiple sources. Computer Speech and Language.
- Special issue on speech separation and recognition in multisource environments. Computer Speech and Language.
- The PASCAL CHiME speech separation and recognition challenge. Computer Speech and Language.
- Combining speech fragment decoding and adaptive noise floor modelling.. IEEE Transactions on Audio, Speech and Language Processing, 20, 818-827.
- Crowdsourcing for word recognition in noise. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 3049-3052.
- Speech fragment decoding techniques for simultaneous speaker identification and speech recognition. COMPUT SPEECH LANG, 24(1), 94-111.
- Energetic and Informational Masking Effects in an Audiovisual Speech Recognition System. IEEE T AUDIO SPEECH, 17(3), 446-458.
- Stream weight estimation for multistream audio-visual speech recognition in a multispeaker environment. SPEECH COMMUN, 50(4), 337-353.
- Improving source localisation in multi-source, reverberant conditions: exploiting local spectro-temporal location cues.. Abstract for Acoust. Soc. Am. mtg.
- The foreign language cocktail party problem: Energetic and informational masking effects in non-native speech perception.. J Acoust Soc Am, 123(1), 414-427.
- Exploiting correlogram structure for robust speech recognition with multiple speech sources. SPEECH COMMUN, 49(12), 874-891. View this article in WRRO
- Modelling speaker intelligibility in noise. SPEECH COMMUN, 49(5), 402-417.
- An automatic speech recognition system based on the scene analysis account of auditory perception. SPEECH COMMUN, 49(5), 384-401.
- An audio-visual corpus for speech perception and automatic speech recognition.. J Acoust Soc Am, 120(5 Pt 1), 2421-2424.
- Mask estimation for missing data speech recognition based on statistics of binaural interaction. IEEE T AUDIO SPEECH, 14(1), 58-67.
- Decoding speech in the presence of other sources. SPEECH COMMUN, 45(1), 5-25.
- Techniques for handling convolutional distortion with 'missing data' automatic speech recognition. SPEECH COMMUN, 43(1-2), 123-142.
- Machine recognition of sounds in mixtures. The Journal of the Acoustical Society of America, 113(4), 2230-2230.
- Is the sine-wave speech cocktail party worth attending?. Speech Communication, 27, 159-174.
- Is the sine-wave speech cocktail party worth attending?. SPEECH COMMUNICATION, 27(3-4), 159-174.
- Modelling the recognition of sine-wave sentences. BRITISH JOURNAL OF AUDIOLOGY, 31(2), 112-113.
- Modeling the recognition of sine-wave sentences. Journal of the Acoustical Society of America, 100, 2682-2682.
- Clarity: Machine Learning Challenges to Revolutionise Hearing Device
Processing.
Chapters
- The CHiME Challenges: Robust Speech Recognition in Everyday Environments, New Era for Robust Speech Recognition (pp. 327-344). Springer International Publishing
- Multichannel Spatial Clustering Using Model-Based Source Separation, New Era for Robust Speech Recognition (pp. 51-77). Springer International Publishing
- Crowdsourcing in Speech Perception In Eskanazi M, Levow G-A, Meng H, Parent G & Sundermann D (Ed.), Crowdsourcing for Speech Processing (pp. 137-169). John Wiley and Sons
- Missing Data Techniques: Recognition with Incomplete Spectrograms In Virtanen T, Singh R & Raj B (Ed.), Techniques for Noise Robustness in Automatic Speech Recognition (pp. 371-398). Wiley
- Robust automatic speech recognition In Wang D-L & Brown GJ (Ed.), Computational Auditory Scene Analysis: Principals, Algorithms and Applications (pp. 297-350). Wiley/IEEE Press
Conference proceedings papers
- The 2nd Clarity Prediction Challenge: A Machine Learning Challenge for Hearing Aid Intelligibility Prediction. ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 14 April 2024 - 19 April 2024.
- The ICASSP SP Cadenza Challenge: Music Demixing/Remixing for Hearing Aids. 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) (pp 93-94), 14 April 2024 - 19 April 2024.
- Using Speech Foundational Models in Loss Functions for Hearing Aid Speech Enhancement. European Signal Processing Conference (pp 421-425)
- The 2nd Clarity Enhancement Challenge for Hearing Aid Speech Intelligibility Enhancement: Overview and Outcomes. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4 June 2023 - 10 June 2023.
- Overview of the 2023 ICASSP SP Clarity Challenge: Speech Enhancement for Hearing Aids. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4 June 2023 - 10 June 2023.
- The First Cadenza Signal Processing Challenge: Improving Music for Those With a Hearing Loss. CEUR Workshop Proceedings, Vol. 3528
- Improved Simulation of Realistically-Spatialised Simultaneous Speech Using Multi-Camera Analysis in The Chime-5 Dataset. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 23 May 2022 - 27 May 2022.
- Auditory-Based Data Augmentation for end-to-end Automatic Speech Recognition. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 23 May 2022 - 27 May 2022.
- MULTI-MODAL ACOUSTIC-ARTICULATORY FEATURE FUSION FOR DYSARTHRIC SPEECH RECOGNITION. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Vol. 2022-May (pp 7372-7376)
- SNuC: The Sheffield Numbers Spoken Language Corpus. 2022 Language Resources and Evaluation Conference, LREC 2022 (pp 1978-1984)
- Predicting Speech Intelligibility for People with Hearing Loss: The Clarity Challenges. Internoise 2022 - 51st International Congress and Exposition on Noise Control Engineering
- Optimising hearing aid fittings for speech in noise with a differentiable hearing loss model. Interspeech 2021 (pp 691-695). Brno, Czechia, 30 August 2021 - 3 September 2021.
- Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism. ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 6 June 2021 - 11 June 2021.
- DHASP: Differentiable Hearing Aid Speech Processing, Vol. 00 (pp 296-300)
- The use of Voice Source Features for Sung Speech Recognition. ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 6 June 2021 - 11 June 2021.
- Modelling the Effects of Hearing Aid Algorithms on Speech and Speaker Intelligibility as Perceived by Listeners with Simulated Sensorineural Hearing Impairment. SoutheastCon 2021, 10 March 2021 - 13 March 2021.
- On End-to-end Multi-channel Time Domain Speech Separation in Reverberant Environments. ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4 May 2020 - 8 May 2020.
- Deep learning of articulatory-based representations and applications for improving dysarthric speech recognition. Speech Communication - 13th ITG-Fachtagung Sprachkommunikation (pp 331-335)
- Source Domain Data Selection for Improved Transfer Learning Targeting Dysarthric Speech Recognition. ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4 May 2020 - 8 May 2020. View this article in WRRO
- Exploring Appropriate Acoustic and Language Modelling Choices for Continuous Dysarthric Speech Recognition. ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4 May 2020 - 8 May 2020. View this article in WRRO
- Phonetic Analysis of Dysarthric Speech Tempo and Applications to Robust Personalised Dysarthric Speech Recognition. ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 12 May 2019 - 17 May 2019.
- Exploring the use of group delay for generalised VTS based noise compensation. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing Proceedings, 15 April 2018 - 20 April 2018. View this article in WRRO
- Robust Source-Filter Separation of Speech Signal in the Phase Domain. Proceedings of the Annual Conference of the International Speech Communication Association View this article in WRRO
- Statistical normalisation of phase-based feature representation for robust speech recognition. 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 5 March 2017 - 9 March 2017. View this article in WRRO
- A Data Driven Approach to Audiovisual Speech Mapping (pp 331-342)
- Source-filter separation of speech signal in the phase domain. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Vol. 2015-January (pp 598-602) View this article in WRRO
- Exploiting synchrony spectra and deep neural networks for noise-robust automatic speech recognition. 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 13 December 2015 - 17 December 2015. View this article in WRRO
- Chime-home: A dataset for sound source recognition in a domestic environment. 2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 18 October 2015 - 21 October 2015.
- Investigating the Impact of Artificial Enhancement of Lip Visibility on the Intelligibility of Spectrally-Distorted Speech. FAAVSP-2015 (pp 93-98), 11 September 2015 - 13 September 2015.
- The third ‘CHiME’ speech separation and recognition challenge: Dataset, task and baselines. 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 13 December 2015 - 17 December 2015.
- A framework for the evaluation of microscopic intelligibility models. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Vol. 2015-January (pp 2558-2562)
- The effect of cochlear implant processing on speaker intelligibility: A perceptual study and computer model. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Vol. 2015-January (pp 1566-1570)
- Long-Term Statistical Feature Extraction from Speech Signal and Its Application in Emotion Recognition (pp 173-184)
- Speech pre-enhancement using a discriminative microscopic intelligibility model. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (pp 2068-2072)
- A fragment-decoding plus missing-data imputation system evaluated on the 2nd CHiME challenge. Proceedings of the 2nd CHiME Workshop on Machine Listening in Multisource Environments (pp 53-58)
- The second ‘CHiME’ Speech Separation and Recognition Challenge: Datasets, tasks and baselines. Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE
- Coupling identification and reconstruction of missing features for noise-robust automatic speech recognition. 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012, Vol. 3 (pp 2637-2640)
- Combining missing-data reconstruction and uncertainty decoding for robust speech recognition. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp 4693-4696)
- Recent advances in fragment-based speech recognition in reverberant multisource environments.. Proceedings of ISCA Workshop on Machine Listening in Multisource Environments (pp 68-73)
- Binaural cues for fragment-based speech recognition in reverberant multisource environments. Proceedings of INTERSPEECH 2011 (pp 1657-1660)
- Incorporating localisation cues in a fragment decoding framework for distant binaural speech recognition.. IEEE Joint Workshop on Hands-Free Speech Communication and Microphone Arrays (HSCMA’11) (pp 207-212)
- Crowdsourcing for word recognition in noise. 12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5 (pp 3056-+)
- Binaural cues for fragment-based speech recognition in reverberant multisource environments. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (pp 1657-1660)
- A pitch based noise estimation technique for robust speech recognition with missing data. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp 4808-4811)
- Distant microphone speech recognition in a noisy indoor environment: combining soft missing data and speech fragment decoding.. ISCA Tutorial and Research Workshop on Statistical And Perceptual Audition
- Robust Formant Estimation: Increasing the Reliability by Comparison among three Methods. Proceedings of the International Conference on Circuits, Systems and Signals, (Recent Advances in Circuits, Sistems and Signals) (pp 341-344)
- An Approach to Vocal Tract Length Normalization by Robust Formant Estimation. Proceedings of the International Conference on Circuits, Systems and Signals, (Recent Advances in Circuits, Sistems and Signals) (pp 345-348)
- Speaker turn tracking with mobile microphones: Combining location and pitch information. European Signal Processing Conference (pp 954-958)
- Robust automatic transcription of english speech corpora. 2010 8th International Conference on Communications, COMM 2010 (pp 79-82)
- The CHiME corpus: A resource and a challenge for computational hearing in multisource environments. Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010 (pp 1918-1921)
- Integrating Hidden Markov Model and PRAAT: A toolbox for robust automatic speech transcription. Proceedings of SPIE - The International Society for Optical Engineering, Vol. 7745
- Using location cues to track speaker changes from mobile, binaural microphones. INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5 (pp 124-127)
- A SPEECH FRAGMENT APPROACH TO LOCALISING MULTIPLE SPEAKERS IN REVERBERANT ENVIRONMENTS. 2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS (pp 4593-4596)
- The CAVA corpus: synchronised stereoscopic and binaural datasets with head movements.. ICMI (pp 109-116)
- Audio-visual speech fragment decoding. Proceedings of the International Conference on Auditory-Visual Speech Processing (AVSP 2007)
- Applying word duration constraints by using unrolled HMMs. INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4 (pp 353-356)
- Integrating pitch and localisation cues at a speech fragment level. INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4 (pp 2752-2755)
- Speech separation based on the statistics of binaural auditory features. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Vol. 5
- Recognition of reverberant speech using full cepstral features and spectral missing data. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Vol. 1
- Audio-Visual Speech Recognition in the Presence of a Competing Speaker. INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5 (pp 1292-1295)
- A Multipitch Tracker for Monaural Speech Segmentation. INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5 (pp 1678-1681)
- Recent advances in speech fragment decoding techniques. INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5 (pp 85-88)
- Recognition of reverberant speech using full cepstral features and spectral missing data. 2006 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-13 (pp 289-292)
- Speech separation based on the statistics of binaural auditory features. 2006 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-13 (pp 5807-5810)
- Recognition of reverberant speech using full cepstral features and spectral missing data. 2006 IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol I, Proceedings (pp 289-292). Toulouse, FRANCE, 14 May 2006 - 19 May 2006.
- Speech separation based on the statistics of binaural auditory features. 2006 IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol V, Proceedings (pp 949-952)
- Soft harmonic masks for recognising speech in the presence of a competing speaker. 9th European Conference on Speech Communication and Technology (pp 2641-2644)
- Binaural feature selection for missing data speech recognition. 9th European Conference on Speech Communication and Technology (pp 1269-1272)
- Recognising speech in the presence of a competing speaker using a 'speech fragment decoder'. 2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5 (pp 425-428)
- Tracking facial markers with an adaptive marker collocation model. 2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5 (pp 665-668)
- Mask estimation based on sound localisation for missing data speech recognition. 2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5 (pp 537-540)
- A Missing Data Approach for Robust Automatic Speech Recognition in the Presence of Reverberation. Proceedings of the 18th International Congress on Acoustics (ICA) (pp 449-452)
- Temporal integration as a consequence of multi-source decoding. Proceedings of the ISCA Workshop on the Temporal Integration in the Perception of Speech (TIPS)
- Missing data speech recognition in reverberant conditions. 2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS (pp 65-68)
- Combining bottom-up and top-down constraints for robust ASR: The multisource decoder. Proceedings of Workshop on consistent and reliable acoustic cues for sound analysis (CRAC-01)
- From Missing Data to Maybe Useful Data: Soft Data Modelling for Noise Robust ASR. Proceedings of the Worshop on Innovation in Speech Processing (WISP 2001)
- Handling Missing and Unreliable Information in Speech Recognition. Proceedings of the 8th International Workshop on Artificial Intelligence and Statistics (AISTATS-2001)
- Linking Auditory Scene Analysis and Robust ASR by Missing Data Techniques. Proceedings of the Worshop on Innovation in Speech Processing (WISP 2001)
- Robust ASR based on clean speech models: an evaluation of missing data techniques for connected digit recognition in noise.. INTERSPEECH (pp 213-217)
- A neural oscillator sound separator for missing data speech recognition. Proceedings of the International Joint Conference on Neural Networks, Vol. 4 (pp 2907-2912)
- A neural oscillator sound separator for missing data speech recognition. IJCNN'01: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS (pp 2907-2912)
- Soft decisions in missing data techniques for robust automatic speech recognition.. INTERSPEECH (pp 373-376)
- Decoding speech in the presence of other sound sources.. INTERSPEECH (pp 270-273)
- Evidence of correlation between acoustic and visual features of speech. Proc. ICPhS ’99
- Estimation of speech acoustics from visual speech features: A comparison of linear and non-linear models. Proceedings of the ISCA Workshop on Auditory-Visual Speech Processing (AVSP) ’99
- Is primitive AV coherence an aid to segment the scene?. Proceedings of the ISCA Workshop on Auditory-Visual Speech Processing (AVSP) ’98
- Acoustic confidence measures for segmenting broadcast news.. ICSLP
- Modelling the recognition of spectrally reduced speech.. EUROSPEECH
- Non-intrusive speech intelligibility prediction for hearing-impaired users using intermediate ASR features and human memory models. 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2024). Seoul, Korea, 14 April 2024 - 14 April 2024. View this article in WRRO
- On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training. Interspeech 2022
- Dysarthric Speech Recognition From Raw Waveform with Parametric CNNs. Interspeech 2022
- Modelling Turn-taking in Multispeaker Parties for Realistic Data Simulation. Interspeech 2022
- Unsupervised Uncertainty Measures of Automatic Speech Recognition for Non-intrusive Speech Intelligibility Prediction. Interspeech 2022
- Exploiting Hidden Representations from a DNN-based Speech Recogniser for Speech Intelligibility Prediction in Hearing-impaired Listeners. Interspeech 2022
- The 1st Clarity Prediction Challenge: A machine learning challenge for hearing aid intelligibility prediction. Interspeech 2022
- Teacher-Student MixIT for Unsupervised and Semi-Supervised Speech Separation. Interspeech 2021
- Parental Spoken Scaffolding and Narrative Skills in Crowd-Sourced Storytelling Samples of Young Children. Interspeech 2021
- Clarity-2021 Challenges: Machine Learning Challenges for Advancing Hearing Aid Processing. Interspeech 2021
- Simulating Realistically-Spatialised Simultaneous Speech Using Video-Driven Speaker Detection and the CHiME-5 Dataset. Interspeech 2020
- Automatic Lyric Transcription from Karaoke Vocal Tracks: Resources and a Baseline System. Interspeech 2019
- The Fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, Task and Baselines. Interspeech 2018
- DNN Driven Speaker Independent Audio-Visual Mask Estimation for Speech Separation. Interspeech 2018
- On the Usefulness of the Speech Phase Spectrum for Pitch Extraction. Interspeech 2018 View this article in WRRO
- Channel Compensation in the Generalised Vector Taylor Series Approach to Robust ASR. Interspeech 2017 View this article in WRRO
- Binary Mask Estimation Strategies for Constrained Imputation-Based Speech Enhancement. Interspeech 2017
- Use of Generalised Nonlinearity in Vector Taylor Series Noise Compensation for Robust Speech Recognition. Interspeech 2016 View this article in WRRO
- Multichannel Spatial Clustering for Robust Far-Field Automatic Speech Recognition in Mismatched Conditions. Interspeech 2016
- Language Effects in Noise-Induced Word Misperceptions. Interspeech 2016
- Misperceptions Arising from Speech-in-Babble Interactions. Interspeech 2016
- Data compression techniques in image compression for multimedia systems. Southcon/96 Conference Record
- Autoencoder bottleneck features with multi-task optimisation for improved continuous dysarthric speech recognition. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH View this article in WRRO
- Towards Solving the Cocktail Party Problem through Primitive Grouping and Model Combination. Proceedings of Forum Acusticum
Posters
- A comparison of audiovisual and auditory-only training on the perception of spectrally-distorted speech. 18th International Congress of Phonetic Sciences.
Theses / Dissertations
- The relationship between auditory organisation and speech perception: Studies with spectrally reduced speech.
Other
- POPeye: Real-time, binaural sound source localisation on an audio-visual robot-head.
- Simultaneous Tracking of Perceiver Movements and Speaker Changes Using Head-Centered, Binaural Data.
Preprints
- The first Cadenza challenges: using machine learning competitions to improve music for listeners with a hearing loss, arXiv.
- Using Speech Foundational Models in Loss Functions for Hearing Aid Speech Enhancement, arXiv.
- Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge, arXiv.
- Non-Intrusive Speech Intelligibility Prediction for Hearing-Impaired Users using Intermediate ASR Features and Human Memory Models, arXiv.
- Overview Of The 2023 Icassp Sp Clarity Challenge: Speech Enhancement For Hearing Aids, arXiv.
- The First Cadenza Signal Processing Challenge: Improving Music for Those With a Hearing Loss, arXiv.
- The Cadenza ICASSP 2024 Grand Challenge, arXiv.
- Auditory-Based Data Augmentation for End-to-End Automatic Speech Recognition, arXiv.
- CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for
Unsegmented Recordings, arXiv.
- DNN driven Speaker Independent Audio-Visual Mask Estimation for Speech
Separation, arXiv.
- The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset,
task and baselines, arXiv.
- Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge. Computer Speech & Language, 89, 101685-101685.
- Grants
-
Current grants
- EnhanceMusic: Machine Learning Challenges to Revolutionise Music Listening for People with Hearing Loss, EPSRC, 06/2022 - 11/2026, £377,568, as PI
- Challenges to Revolutionise Hearing Device Processing, EPSRC, 10/2019 to 10/2025, £480,416, as PI
- UKRI Centre for Doctoral Training in Speech and Language Technologies and their Applications, EPSRC, 04/2019 to 09/2027, £5,508,850, as Co-PI
- TAPAS: Training Network on Automatic Processing of PAthological Speech, EC H2020, 11/2017 to 06/2022, £468,000, as Co-PI
Previous grants
- Deep learning of articulatory-based representations of dysarthric speech, Google, 02/2016 to 01/2017, £46,624, as Co-PI
- Towards visually-driven speech enhancement for cognitively-inspired multi-modal hearing-aid devices (AV-COGHEAR), EPSRC, 10/2015 to 09/2018, £125,493, as PI
- INSPIRE: Investigating Speech In Real Environments, EC FP7, 01/2012 to 12/2015, £308,473, as PI
- ACAS: Analysis of Complex Acoustic Scenes, EPSRC, 07/2010 to 09/2010, £9,978, as PI
- CHIME: Computational Hearing in Multisource Environments, EPSRC, 06/2009 to 05/2012, £326,245, as PI
- Audio-Visual Speech Recognition in the Presence of Non-Stationary Noise, EPSRC, 02/2005 to 05/2007, £116,853, as PI
- Professional activities and memberships
-
- Member of the Speech and Hearing research group
- Co-founder of the CHiME series of International Workshops and Robust Speech Recognition Evaluations, 2011 onwards.
- EURASIP Best Paper Award, 2009; for best paper in Speech Communication during 2005.
- ISCA Best Paper Award, 2008; for best paper in Speech Communication 2005-2007.