| Discriminative neural clustering for speaker diarisation Q Li, FL Kreyssig, C Zhang, PC Woodland SLT, 574-581, 2021 | 44 | 2021 |
| Generative modeling of audible shapes for object perception Z Zhang, J Wu, Q Li, Z Huang, J Traer, JH McDermott, JB Tenenbaum, ... ICCV, 1251-1260, 2017 | 39 | 2017 |
| Confidence estimation for attention-based sequence-to-sequence models for speech recognition Q Li, D Qiu, Y Zhang, B Li, Y He, PC Woodland, L Cao, T Strohman ICASSP, 6388-6392, 2021 | 38 | 2021 |
| Confidence estimation and deletion prediction using bidirectional recurrent neural networks A Ragni, Q Li, MJF Gales, Y Wang SLT, 204-211, 2018 | 37 | 2018 |
| Bi-directional lattice recurrent neural networks for confidence estimation Q Li, PM Ness, A Ragni, MJF Gales ICASSP, 6755-6759, 2019 | 30 | 2019 |
| Shape and material from sound Z Zhang, Q Li, Z Huang, J Wu, JB Tenenbaum, WT Freeman NIPS, 1278-1288, 2017 | 28 | 2017 |
| Learning word-level confidence for subword end-to-end ASR D Qiu, Q Li, Y He, Y Zhang, B Li, L Cao, R Prabhavalkar, D Bhatia, W Li, ... ICASSP, 6393-6397, 2021 | 27 | 2021 |
| Integrating source-channel and attention-based sequence-to-sequence models for speech recognition Q Li, C Zhang, PC Woodland ASRU, 39-46, 2019 | 20 | 2019 |
| Knowledge distillation for neural transducers from large self-supervised pre-trained models X Yang, Q Li, PC Woodland ICASSP, 8527-8531, 2022 | 17 | 2022 |
| Residual energy-based models for end-to-end speech recognition Q Li, Y Zhang, B Li, L Cao, PC Woodland Interspeech, 4069-4073, 2021 | 13 | 2021 |
| Multi-task learning for end-to-end ASR word and utterance confidence with deletion prediction D Qiu, Y He, Q Li, Y Zhang, L Cao, I McGraw Interspeech, 4074-4078, 2021 | 12 | 2021 |
| PyHTK: Python library and ASR pipelines for HTK C Zhang, FL Kreyssig, Q Li, PC Woodland ICASSP, 6470-6474, 2019 | 12 | 2019 |
| Combining hybrid DNN-HMM ASR systems with attention-based models using lattice rescoring Q Li, C Zhang, PC Woodland Speech Communication 147, 12-21, 2023 | 6 | 2023 |
| Improving confidence estimation on out-of-domain data for end-to-end speech recognition Q Li, Y Zhang, D Qiu, Y He, L Cao, PC Woodland ICASSP, 6537-6541, 2022 | 6 | 2022 |
| Combining frame-synchronous and label-synchronous systems for speech recognition Q Li, C Zhang, PC Woodland arXiv preprint arXiv:2107.00764, 2021 | 4 | 2021 |
| Knowledge distillation from multiple foundation models for end-to-end speech recognition X Yang, Q Li, C Zhang, PC Woodland arXiv preprint arXiv:2303.10917, 2023 | 2 | 2023 |
| Learning word-level confidence for subword end-to-end automatic speech recognition D Qiu, Q Li, Y He, Y Zhang, B Li, L Cao, R Prabhavalkar, D Bhatia, W Li, ... US Patent App. 17/182,592, 2022 | 2 | 2022 |
| Increasing context for estimating confidence scores in automatic speech recognition A Ragni, MJF Gales, O Rose, K Knill, A Kastanos, Q Li, P Ness IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2022 | 2 | 2022 |
| Confidence scores for speech processing Q Li Cambridge University Engineering Department, 2018 | 2 | 2018 |
| Modular domain adaptation for Conformer-based streaming ASR Q Li, B Li, D Hwang, TN Sainath, PM Mengibar arXiv preprint arXiv:2305.13408, 2023 | 1 | 2023 |
Philip WoodlandProfessor of Information Engineering, Cambridge University Engineering DepartmentVerified email at eng.cam.ac.uk
