July 26, 2022
This paper presents recent progress on integrating speech separation and enhancement (SSE) into the ESPnet toolkit. Compared with the previous ESPnet-SE work, numerous features have been added, including recent state-of-the-art speech enhancement models with their respective training and evaluation recipes. Importantly, a new interface has been designed to flexibly combine speech enhancement front-ends with other tasks, including automatic speech recognition (ASR), speech translation (ST), and spoken language understanding (SLU). To showcase such integration, we performed experiments on carefully designed synthetic datasets for noisy-reverberant multichannel ST and SLU tasks, which can be used as benchmark corpora for future research. In addition to these new tasks, we also use CHiME-4 and WSJ0-2Mix to benchmark multi and single-channel SE approaches. Results show that the integration of SE front-ends with back-end tasks is a promising research direction even for tasks besides ASR, especially in the multi-channel scenario. The code is available online at https://github.com/ESPnet/ESPnet. The multichannel ST and SLU datasets, which are another contribution of this work, are released on HuggingFace.
Written by
Brian Yan
Chenda Li
Robin Scheibler
Samuele Cornell
Shinji Watanabe
Wangyou Zhang
Xuankai Chang
Yanming Qian
Yen-Ju Lu
Yoshiki Masuyama
Yu Tsao
Zhong-Qiu Wang
Publisher
INTERSPEECH
Foundational models
Our approach
Latest news
Foundational models