SegAug: CTC-Aligned Segmented Augmentation For Robust RNN-Transducer Based Speech RecognitionIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2025 |
Mamba for Streaming ASR Combined with Unimodal AggregationIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024 Ying Fang Xiaofei Li |
Towards Automatic Data Augmentation for Disordered Speech RecognitionIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023 |
Align With Purpose: Optimize Desired Properties in CTC Models with a
General Plug-and-Play FrameworkInternational Conference on Learning Representations (ICLR), 2023 |
ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMsInterspeech (Interspeech), 2023 |