Research output per year
Research output per year
Personal profile
Research Interests
My primary research focus is on automatic speech recognition (ASR). I am particularly interested the following topics:
- methods for cross-domain and cross-lingual adaptation
- regularisation methods, particularly multi-task learning
- algorithms for efficient alignment and search of audio data
- lightly supervised and semi-supervised training
- end-to-end and raw-waveform methods
- ASR systems for minority or under-resourced languages
- speech recognition and alignment of broadcast media
Qualifications
2010, PhD in Automatic Speech Recognition, University of Edinburgh.
2005, MPhil, Computer Speech, Text and Internet Technology, University of Cambridge.
2002, BA, Mathematics, University of Cambridge.
Biography
Peter Bell is a Reader in Speech Technology in the Centre for Speech Technology Research (CSTR) in the School of Informatics. His research covers many different aspects of acoustic modelling for speech recognition. After receiving MA and MPhil degrees from Cambridge University, he obtained his PhD from Edinburgh in 2010, supervised by Prof Simon King. Since graduating, he has continued his research at CSTR, working primarily with Prof Steve Renals on several large projects funded by EPSRC, H2020 and others. He is currently Co-Investigator on the IARPA-funded MATERIAL programme and the EPSRC-funded SpeechWave project. From 2012-2019, Peter divided his time between the academic and commerical worlds as part-time speech scientist at Quorate Technology Ltd. He carries out consultancy for a number of other companies.
Fingerprint
Dive into the research topics where Peter Bell is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
- 1 Similar Profiles
Collaborations and top research areas from the last five years
Recent external collaboration on country/territory level. Dive into details by clicking on the dots or
-
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 AccessFile -
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 AccessFile -
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 AccessFile -
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 AccessFile -
Comparison and analysis of new curriculum criteria for end-to-end ASR
Karakasidis, G., Kurimo, M., Bell, P. & Grósz, T., Sept 2024, In: Speech Communication. 103113.Research output: Contribution to journal › Article › peer-review
Open AccessFile
Activities
- 1 Participation in conference
-
UK and Ireland Speech Workshop 2022
Lai, C. (Chair) & Bell, P. (Chair)
5 Sept 2022 → 6 Sept 2022Activity: Participating in or organising an event types › Participation in conference
Prizes
-
Best student paper at Interspeech 2022
Wallbridge, S. (Recipient), Bell, P. (Recipient) & Lai, C. (Recipient), 22 Sept 2022
Prize: Prize (including medals and awards)
-
PV160 - Transcripts and AI summaries for deaf pupils and others with additional support needs
Bell, P. (Principal Investigator)
Engineering and Physical Sciences Research Council
1/02/24 → 30/06/25
Project: Research
-
Transcripts and AI summaries for deaf pupils and others with additional support needs
Bell, P. (Principal Investigator) & O'Neill, R. (Co-investigator)
Economic and Social Research Council
1/02/24 → 30/06/25
Project: Research
-
Gaelic Speech Recognition for Media, Education and Research
Bell, P. (Principal Investigator), Alex, B. (Co-investigator) & Lamb, W. (Co-investigator)
31/03/23 → 31/07/25
Project: Research
-
Analysis and Processing of non-incident voice calls
Bell, P. (Principal Investigator)
Engineering and Physical Sciences Research Council
1/01/24 → 30/06/24
Project: Research
-
EPSRC IAA PDRA extensions
Mount, A. (Principal Investigator), Bell, P. (Co-investigator), Camp, P. (Co-investigator), Elfick, A. (Co-investigator), Hands, P. (Co-investigator) & Roy, D. (Co-investigator)
Engineering and Physical Sciences Research Council
1/04/23 → 17/09/23
Project: Research
Datasets
-
The Edinburgh International Accents of English Corpus
Bell, P. (Creator), Klejch, O. (Creator), Carmantini, A. (Creator), Markl, N. (Creator), Bogoychev, N. (Creator) & Sanabria Teixidor, R. (Creator), Edinburgh DataShare, 15 Apr 2025
DOI: 10.7488/ds/7914
Dataset
Press/Media
-
Woman stunned as AI fills message with profanity: 'been able to have sex'
12/03/25
1 Media contribution
Press/Media: Research
-
AI stuns grandma with vicious verbal attack - and questions about her sex life: 'I was shocked'
10/03/25
1 Media contribution
Press/Media: Research
-
Grandmother, 66, gets a shock after Apple's AI calls her a 'piece of s***'
10/03/25
1 Media contribution
Press/Media: Research
-
-