Noise-Robust Speech Recognition With 10 Minutes Unparalleled In-Domain Data

Chen Chen; Nana Hou; Yuchen Hu; Shashank Shirol; Eng Siong Chng

ICASSP 2022accepted0 citations

Noise-Robust Speech Recognition With 10 Minutes Unparalleled In-Domain Data

Chen Chen, Nana Hou, Yuchen Hu, Shashank Shirol, Eng Siong Chng

Abstract

Noise-robust speech recognition systems require large amounts of training data including noisy speech data and corresponding transcripts to achieve state-of-the-art performances in face of various practical environments. However, such plenty of in-domain data is not always available in the real-life world. In this paper, we propose a generative adversarial network to simulate noisy spectrum from the clean spectrum (SimuGAN), where only 10 minutes of unparalleled in-domain noisy speech data is required as labels. Furthermore, we also propose a dual-path speech recognition system to improve the robustness of the system under noisy conditions. Experimental results show that the proposed speech recognition system achieves 7.3% absolute improvement with simulated noisy data by Simu-GAN over the best baseline in terms of word error rate (WER).

BibTeX

@inproceedings{icassp2022_noiserobustspeec,
  title = {Noise-Robust Speech Recognition With 10 Minutes Unparalleled In-Domain Data},
  author = {Chen Chen and Nana Hou and Yuchen Hu and Shashank Shirol and Eng Siong Chng},
  booktitle = {ICASSP 2022},
  year = {2022}
}