Word error rate (WER) and character error rate (CER) are standard metric...
This paper introduces a new speech dataset called “LibriTTS-R” designed ...
Speech restoration (SR) is a task of converting degraded speech signals ...
End-to-end speech recognition is a promising technology for enabling com...
This study aims to improve the performance of automatic speech recogniti...
Single-channel speech enhancement (SE) is an important task in speech
pr...
End-to-end (E2E) modeling is advantageous for automatic speech recogniti...
This paper describes the recent development of ESPnet
(https://github.co...
We present an approach for unsupervised learning of speech representatio...
We present ESPnet-ST, which is designed for the quick development of
spe...
Sequence-to-sequence models have been widely used in end-to-end speech
p...
This paper introduces a new open source platform for end-to-end speech
p...