8 papers
Qwen-Audio-Jev: A Unified Interface for Audio Decisions
Peixin Chen, Ying Fang, Zhifu Gao +19
Large audio language models (LALMs) have made substantial progress in audio understanding. However, autoregressive text generation introduces computational overhead and latency in…
UMA-Split: unimodal aggregation for both English and Mandarin non-autoregressive speech recognition
Ying Fang, Xiaofei Li
This paper proposes a unimodal aggregation (UMA) based nonautoregressive model for both English and Mandarin speech recognition. The original UMA explicitly segments and aggregates…
CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR
Nian Shao, Rui Zhou, Pengyu Wang +4
In this work, we propose CleanMel, a single-channel Mel-spectrogram denoising and dereverberation network for improving both speech quality and automatic speech recognition (ASR) p…
VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identification
Pengyu Wang, Ying Fang, Xiaofei Li
Reverberant speech, denoting the speech signal degraded by reverberation, contains crucial knowledge of both anechoic source speech and room impulse response (RIR). This work propo…
Mamba for Streaming ASR Combined with Unimodal Aggregation
Ying Fang, Xiaofei Li
This paper works on streaming automatic speech recognition (ASR). Mamba, a recently proposed state space model, has demonstrated the ability to match or surpass Transformers in var…
RealMAN: A Real-Recorded and Annotated Microphone Array Dataset for Dynamic Speech Enhancement and Localization
Bing Yang, Changsheng Quan, Yabo Wang +7
The training of deep learning-based multichannel speech enhancement and source localization systems relies heavily on the simulation of room impulse response and multichannel diffu…
Mel-FullSubNet: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR
Rui Zhou, Xian Li, Ying Fang +1
In this work, we propose Mel-FullSubNet, a single-channel Mel-spectrogram denoising and dereverberation network for improving both speech quality and automatic speech recognition (…
Unimodal Aggregation for CTC-based Speech Recognition
Ying Fang, Xiaofei Li
This paper works on non-autoregressive automatic speech recognition. A unimodal aggregation (UMA) is proposed to segment and integrate the feature frames that belong to the same te…