1. MEConformer: Highly representative embedding extractor for speaker verification via incorporating selective convolution into deep speaker encoder;Expert Systems with Applications;2024-06
2. Hot-Fixing Wake Word Recognition for End-to-End ASR Via Neural Model Reprogramming;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14
3. LCB-Net: Long-Context Biasing for Audio-Visual Speech Recognition;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14
4. SlideSpeech: A Large Scale Slide-Enriched Audio-Visual Corpus;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14
5. Transducers with Pronunciation-Aware Embeddings for Automatic Speech Recognition;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14