-
Zeyu Zhao, and Peter Bell. “Advancing CTC Models For Better Speech Alignment: A Topological Approach.” IEEE Spoken Language Technology (SLT) Workshop 2024 (accepted). pdf code
-
Zeyu Zhao, Pinzhen Chen, and Peter Bell. “Regarding Topology and Adaptability in Differentiable WFST-Based E2E ASR.” XAI-SA Workshop ICASSP 2024. pdf link code
-
Zeyu Zhao, Peter Bell, and Ondrej Klejch. “Exploring Dominant Paths in CTC-Like ASR Models: Unraveling the Effectiveness of Viterbi Decoding.” XAI-SA Workship ICASSP 2024. pdf link code
-
Zeyu Zhao, and Peter Bell. “Regarding Topology and Variant Frame Rates for Differentiable WFST-based End-to-End ASR.” INTERSPEECH 2023. pdf link code
-
Yuanchao Li*, Zeyu Zhao*, Ondrej Klejch, Peter Bell, and Catherine Lai. “ASR and Emotional Speech: A Word-Level Investigation of the Mutual Impact of Speech and Emotion Recognition” INTERSPEECH 2023. pdf link
-
Zeyu Zhao, and Peter Bell. “Investigating Sequence-Level Normalisation For CTC-Like End-to-End ASR.” ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2022. pdf link
-
Zeyu Zhao, and Wei-Qiang Zhang. “End-to-End Keyword Search Based on Attention and Energy Scorer for Low Resource Languages.” INTERSPEECH. 2020. pdf link
-
Zeyu Zhao, et al. “Jujubecake: An Extension of LSTM Considering Correlation among Input Blocks.” 2020 15th IEEE International Conference on Signal Processing (ICSP). Vol. 1. IEEE, 2020. pdf link