Philip Woodland
University of Cambridge
H-index: 74
Europe-United Kingdom
Top articles of Philip Woodland
Title | Journal | Author(s) | Publication Date |
---|---|---|---|
Graph neural networks for contextual ASR with the tree-constrained pointer generator | IEEE/ACM Transactions on Audio, Speech, and Language Processing | Guangzhi Sun Chao Zhang Philip C Woodland | 2024/4/16 |
FastInject: Injecting Unpaired Text Data into CTC-Based ASR Training | Keqi Deng Philip C Woodland | 2024/4/14 | |
Handling Ambiguity in Emotion: From Out-of-Domain Detection to Distribution Estimation | arXiv preprint arXiv:2402.12862 | Wen Wu Bo Li Chao Zhang Chung-Cheng Chiu Qiujia Li | 2024/2/20 |
Parameter Efficient Finetuning for Speech Emotion Recognition and Domain Adaptation | arXiv preprint arXiv:2402.11747 | Nineli Lashkarashvili Wen Wu Guangzhi Sun Philip C Woodland | 2024/2/19 |
Self-Supervised Learning-Based Source Separation for Meeting Data | Yuang Li Xianrui Zheng Philip C Woodland | 2023/6/4 | |
Integrating Emotion Recognition with Speech Recognition and Speaker Diarisation for Conversations | arXiv preprint arXiv:2308.07145 | Wen Wu Chao Zhang Philip C Woodland | 2023/8/14 |
Label-Synchronous Neural Transducer for Adaptable Online E2E Speech Recognition | arXiv preprint arXiv:2311.11353 | Keqi Deng Philip C Woodland | 2023/11/19 |
Combining hybrid DNN-HMM ASR systems with attention-based models using lattice rescoring | Speech Communication | Qiujia Li Chao Zhang Philip C Woodland | 2023/2/1 |
Adaptable end-to-end ASR models using replaceable internal LMs and residual softmax | Keqi Deng Philip C Woodland | 2023/6/4 | |
Label-synchronous neural transducer for end-to-end ASR | arXiv preprint arXiv:2307.03088 | Keqi Deng Philip C Woodland | 2023/7/6 |
Speech-based Slot Filling using Large Language Models | arXiv preprint arXiv:2311.07418 | Guangzhi Sun Shutong Feng Dongcheng Jiang Chao Zhang Milica Gašić | 2023/11/13 |
Distribution-Based Emotion Recognition in Conversation | Wen Wu Chao Zhang Philip C Woodland | 2023/1/9 | |
End-to-end spoken language understanding with tree-constrained pointer generator | Guangzhi Sun Chao Zhang Philip C Woodland | 2023/6/4 | |
Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Data | arXiv preprint arXiv:2307.01764 | Guangzhi Sun Chao Zhang Ivan Vulić Paweł Budzianowski Philip C Woodland | 2023/7/4 |
Conditional Diffusion Model for Target Speaker Extraction | arXiv preprint arXiv:2310.04791 | Theodor Nguyen Guangzhi Sun Xianrui Zheng Chao Zhang Philip C Woodland | 2023/10/7 |
Spectral Clustering-Aware Learning of Embeddings for Speaker Diarisation | Evonne PC Lee Guangzhi Sun Chao Zhang Philip C Woodland | 2023/6/4 | |
System and method using parameterized speech synthesis to train acoustic models | 2023/1/3 | ||
Estimating the uncertainty in emotion attributes using deep evidential regression | arXiv preprint arXiv:2306.06760 | Wen Wu Chao Zhang Philip C Woodland | 2023/6/11 |
It HAS to be Subjective: Human Annotator Simulation via Zero-shot Density Estimation | arXiv preprint arXiv:2310.00486 | Wen Wu Wenlin Chen Chao Zhang Philip C Woodland | 2023/9/30 |
Can contextual biasing remain effective with Whisper and GPT-2? | arXiv preprint arXiv:2306.01942 | Guangzhi Sun Xianrui Zheng Chao Zhang Philip C Woodland | 2023/6/2 |