Research output per year
Research output per year
Organisation profile
Organisation profile
The Centre for Speech Technology Research (CSTR) is an interdisciplinary research centre linking Informatics and Linguistics and English Language.
Founded in 1984, CSTR is concerned with research in all areas of speech technology including speech recognition, speech synthesis, speech signal processing, spoken language processing, multimodal interfaces, and dialogue systems. We have many collaborations with the wider community of researchers in speech science, language, cognition, and machine learning for which Edinburgh is renowned.
Fingerprint
Dive into the research topics where Centre for Speech Technology Research is active. These topic labels come from the works of this organisation's members. Together they form a unique fingerprint.
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
Profiles
-
Peter Bell
- School of Informatics - Personal Chair of Speech Technology
- Institute of Language, Cognition and Computation
- Centre for Speech Technology Research
- Language, Interaction, and Robotics
Person: Academic: Research Active
-
Simon King
- School of Philosophy, Psychology and Language Sciences - Personal Chair of Speech Processing
- Centre for Speech Technology Research
Person: Academic: Research Active
-
Catherine Lai
- School of Philosophy, Psychology and Language Sciences - Reader
- Institute of Language, Cognition and Computation
- Centre for Speech Technology Research
Person: Academic: Research Active
-
Learning nonlinear dynamics in physical modelling synthesis using neural ordinary differential equations
Zheleznov, V., Bilbao, S., Wright, A. & King, S., 5 Sept 2025, Proceedings of the 28th International Conference on Digital Audio Effects (DAFx25). p. 142-149 8 p. (Proceedings of the International Conference on Digital Audio Effects).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
Open AccessFile -
TTSDS2: Robust objective evaluation for human-quality synthetic speech
Minixhofer, C., Klejch, O. & Bell, P., 27 Aug 2025, Proceedings of the 13th Edition of the Speech Synthesis Workshop. International Speech Communication Association (ISCA), p. 68-75 8 p.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
Open AccessFile -
A practitioner’s guide to building ASR models for low-resource languages: A case study on Scottish Gaelic
Klejch, O., Lamb, W. & Bell, P., 21 Aug 2025, Proceedings of the 26th Interspeech Conference. International Speech Communication Association (ISCA), p. 728-732 5 p. (Interspeech).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
Open AccessFile
Activities
-
Language and Society Scotland: Language & AI
Hall-Lew, L. (Organiser), Ilbury, C. (Organiser), Lai, C. (Invited speaker), Sullivan, E. (Invited speaker) & Markl, N. (Invited speaker)
28 Nov 2025Activity: Participating in or organising an event types › Participation in workshop, seminar, course
-
Across the prosodic dimension: Exploring spoken communication beyond text
Lai, C. (Invited speaker)
11 Sept 2025Activity: Academic talk or presentation types › Invited talk
-
Rui-Chen Zheng
Richmond, K. (Host)
1 Sept 2025 → 30 Apr 2026Activity: Hosting a visitor types › Hosting an academic visitor
Prizes
-
ACL Best Special Theme Paper Award
Richmond, K. (Recipient), 22 May 2022
Prize: Prize (including medals and awards)
-
Best paper award
Zheleznov, V. (Recipient), Bilbao, S. (Recipient), Wright, A. (Recipient) & King, S. (Recipient), 6 Sept 2025
Prize: Prize (including medals and awards)
-
Best student paper at Interspeech 2022
Wallbridge, S. (Recipient), Bell, P. (Recipient) & Lai, C. (Recipient), 22 Sept 2022
Prize: Prize (including medals and awards)
-
MULTIMODAL SELF-SUPERVISED REPRESENTATION LEARNING FOR AUDIO GENERATION
King, S. (Principal Investigator)
1/10/22 → 31/03/26
Project: Research
-
Gaelic Speech Recognition for Media, Education and Research
Lamb, W. (Principal Investigator), Alex, B. (Co-investigator), Bell, P. (Co-investigator) & Ó Maolalaigh, R. (Co-investigator)
31/03/23 → 30/03/25
Project: Research
-
Speech Generation For Indigenous Language Education
Richmond, K. (Principal Investigator)
3/02/23 → 2/12/25
Project: Research
Datasets
-
Lothian Diaries Dataset 1 (May-September 2020)
Hall-Lew, L. (Creator), Cowie, C. (Data Collector), Lai, C. (Data Manager), Liu, S. (Data Collector), Markl, N. (Data Collector), McNulty, S. (Data Collector), Symington, B. (Data Collector), Llewellyn, C. (Data Collector), Fang, N. (Data Collector), Elliott Slosarova, Z. (Data Collector), Klingler, A. (Data Collector) & Hall-Lew, L. (Owner), Edinburgh DataVault, 30 Sept 2022
DOI: 10.7488/7a22cc4b-87ec-4df3-a549-3b347fd4bca5
Dataset
-
[CODE] Pretrained models for ZMM-TTS
Gong, C. (Creator), Wang, X. (Creator), Cooper, E. (Creator), Wells, D. (Creator), Wang, L. (Creator), Dang, J. (Creator), Richmond, K. (Creator) & Yamagishi, J. (Creator), Zenodo, 6 Mar 2024
Dataset
-
Listening-test materials for "Where do the improvements come from in sequence-to-sequence neural TTS?"
Valentini Botinhao, C. (Creator), Fong, J. (Creator), Watts, O. (Creator) & Henter, G. E. (Creator), Edinburgh DataShare, 17 Nov 2020
DOI: 10.7488/ds/2952
Dataset
Press/Media
-
AI initiative gives Gaelic a foothold in the digital age
Lamb, W., Ó Maolalaigh, R., Alex, B. & Bell, P.
8/05/25
1 Media contribution
Press/Media: Press Release
-
Prof Simon King and Dr Philipa Rewaj discuss the Speak:Unique project
King, S. & Rewaj, P.
4/12/16
1 Media contribution
Press/Media: Public Engagement Activities