65 citations · 295 across the 28 of their papers we have counts for
18 papers · 1 filter
CASA-ASR: Context-Aware Speaker-Attributed ASR
Mohan Shi, Zhihao Du, Qian Chen +5
Recently, speaker-attributed automatic speech recognition (SA-ASR) has attracted a wide attention, which aims at answering the question ``who spoke what''. Different from modular s…
Semantic VAD: Low-Latency Voice Activity Detection for Speech Interaction
Mohan Shi, Yuchun Shu, Lingyun Zuo +4
For speech interaction, voice activity detection (VAD) is often used as a front-end. However, traditional VAD algorithms usually need to wait for a continuous tail silence to reach…
Joint Generative-Contrastive Representation Learning for Anomalous Sound Detection
Xiao-Min Zeng, Yan Song, Zhu Zhuo +5
In this paper, we propose a joint generative and contrastive representation learning method (GeCo) for anomalous sound detection (ASD). GeCo exploits a Predictive AutoEncoder (PAE)…
Robust Data2vec: Noise-robust Speech Representation Learning for ASR by Combining Regression and Improved Contrastive Learning
Qiu-Shi Zhu, Long Zhou, Jie Zhang +3
Self-supervised pre-training methods based on contrastive learning or regression tasks can utilize more unlabeled data to improve the performance of automatic speech recognition (A…
Joint Training of Speech Enhancement and Self-supervised Model for Noise-robust ASR
Qiu-Shi Zhu, Jie Zhang, Zi-Qiang Zhang +1
Speech enhancement (SE) is usually required as a front end to improve the speech quality in noisy environments, while the enhanced speech might not be optimal for automatic speech…
Supervised and Self-supervised Pretraining Based COVID-19 Detection Using Acoustic Breathing/Cough/Speech Signals
Xing-Yu Chen, Qiu-Shi Zhu, Jie Zhang +1
In this work, we propose a bi-directional long short-term memory (BiLSTM) network based COVID-19 detection method using breath/speech/cough signals. By using the acoustic signals t…