40 citations · 180 across the 45 of their papers we have counts for
6 papers · 1 filter
The 2020 ESPnet update: new features, broadened applications, performance improvements, and future plans
Shinji Watanabe, Florian Boyer, Xuankai Chang +12
This paper describes the recent development of ESPnet (https://github.com/espnet/espnet), an end-to-end speech processing toolkit. This project was initiated in December 2017 to ma…
Context-aware RNNLM Rescoring for Conversational Speech Recognition
Kun Wei, Pengcheng Guo, Hang Lv +2
Conversational speech recognition is regarded as a challenging task due to its free-style speaking and long-term contextual dependencies. Prior work has explored the modeling of lo…
Adversarial Training for Multi-domain Speaker Recognition
Qing Wang, Wei Rao, Pengcheng Guo +1
In real-life applications, the performance of speaker recognition systems always degrades when there is a mismatch between training and evaluation data. Many domain adaptation meth…
Recent Developments on ESPnet Toolkit Boosted by Conformer
Pengcheng Guo, Florian Boyer, Xuankai Chang +12
In this study, we present recent developments on ESPnet: End-to-End Speech Processing toolkit, which mainly involves a recently proposed architecture called Conformer, Convolution-…
Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals
Jing Shi, Xuankai Chang, Pengcheng Guo +5
Neural sequence-to-sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus…
Inaudible Adversarial Perturbations for Targeted Attack in Speaker Recognition
Qing Wang, Pengcheng Guo, Lei Xie
Speaker recognition is a popular topic in biometric authentication and many deep learning approaches have achieved extraordinary performances. However, it has been shown in both im…