New
- 2019.10.31: These webpages were three or four years out of date, I am slowly updating them
- Recent papers:
- Joachim Fainberg, Ondrej Klejch, Steve Renals, and Peter Bell, Lattice-based lightly-supervised acoustic model training, Interspeech 2019.
- Erfan Loweimi, Peter Bell, and Steve Renals. On Learning Interpretable CNNs with Parametric Modulated Kernel-based Filters, Interspeech 2019.
- Andrea Carmantini, Peter Bell, and Steve Renals. Untranscribed web audio for low resource speech recognition, Interspeech 2019.
- Shucong Zhang, Erfan Loweimi, Yumo Xu, Peter Bell, and Steve Renals. Trainable Dynamic Subsampling for End-to-End Speech Recognition, Interspeech 2019.
- Aciel Eshky, M Sam Ribeiro, Korin Richmond, and Steve Renals. Synchronising audio and ultrasound by learning cross-modal embeddings, Interspeech 2019.
- M Sam Ribeiro, Aciel Eshky, Korin Richmond, and Steve Renals. Ultrasound tongue imaging for diarization and alignment of child speech therapy sessions, Interspeech 2019.
- Ben Krause, Emmanuel Kahembwe, Iain Murray, and Steve Renals. Dynamic Evaluation of Transformer Language Models, arXiv:1904.08378
- Erfan Loweimi, Peter Bell, and Steve Renals. On the Usefulness of Statistical Normalisation of Bottleneck Features for Speech Recognition, ICASSP-2019.
- M Sam Ribeiro, Aciel Eshky, Korin Richmond, and Steve Renals. Speaker-Independent Classification of Phonetic Segments from Raw Ultrasound in Child Speech, ICASSP 2019.
- Shucong Zhang, Erfan Loweimi, Peter Bell, and Steve Renals. Windowed Attention Mechanisms for Speech Recognition, ICASSP 2019.
Research
I am currently working on the following topics:
- Deep learning for speech recognition
- Low-resource and multilingual speech recognition
- Speaker diarization
- Clinical applications of speech recognition