| Insights on neural representations for end-to-end speech recognition A Ollerenshaw, MA Jalal, T Hain Interspeech 2021, 4079-4083, 2021 | 8 | 2021 |
| Probing Statistical Representations For End-To-End ASR A Ollerenshaw, MA Jalal, T Hain 2023 31st European Signal Processing Conference (EUSIPCO), 401-405, 2023 | 3 | 2023 |
| Towards domain generalisation in asr with elitist sampling and ensemble knowledge distillation R Ahmad, MA Jalal, MU Farooq, A Ollerenshaw, T Hain ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 2 | 2023 |
| Insights of neural representations in multi-banded and multi-channel convolutional transformers for end-to-end asr A Ollerenshaw, MA Jalal, T Hain 2022 30th European Signal Processing Conference (EUSIPCO), 434-438, 2022 | 2 | 2022 |
| Empirical interpretation of the relationship between speech acoustic context and emotion recognition A Ollerenshaw, MA Jalal, R Milner, T Hain arXiv preprint arXiv:2306.17500, 2023 | 1 | 2023 |
| Dynamic kernels and channel attention for low resource speaker verification A Ollerenshaw, MA Jalal, T Hain arXiv preprint arXiv:2211.02000, 2022 | 1 | 2022 |
| Dynamic kernels and channel attention with multi-layer embedding aggregation for speaker verification A Ollerenshaw, MA Jalal, T Hain arXiv preprint arXiv:2211.02000, 2022 | 1 | 2022 |
| Representation analysis methods to model context for speech technology A Ollerenshaw University of Sheffield, 2023 | | 2023 |
Thomas HainProfessor of Speech Technology, University of SheffieldVerified email at sheffield.ac.uk
Thomas HainProfessor of Speech Technology, University of SheffieldVerified email at sheffield.ac.uk