5 papers
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…
LS-EEND: Long-Form Streaming End-to-End Neural Diarization with Online Attractor Extraction
Di Liang, Xiaofei Li
This work proposes a frame-wise online/streaming end-to-end neural diarization (EEND) method, which detects speaker activities in a frame-in-frame-out fashion. The proposed model m…
Multichannel Long-Term Streaming Neural Speech Enhancement for Static and Moving Speakers
Changsheng Quan, Xiaofei Li
In this work, we extend our previously proposed offline SpatialNet for long-term streaming multichannel speech enhancement in both static and moving speaker scenarios. SpatialNet e…
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 (…
RVAE-EM: Generative speech dereverberation based on recurrent variational auto-encoder and convolutive transfer function
Pengyu Wang, Xiaofei Li
In indoor scenes, reverberation is a crucial factor in degrading the perceived quality and intelligibility of speech. In this work, we propose a generative dereverberation method.…