期刊
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
卷 -, 期 -, 页码 6287-6291出版社
IEEE
DOI: 10.1109/ICASSP43922.2022.9746347
关键词
input switching; speech extraction; speech separation; noise-robust speech recognition; SpeakerBeam
In this work, a DNN-based switching method is proposed to address the performance degradation issue caused by speech enhancement in automatic speech recognition (ASR). By learning to estimate the suitability of enhanced or observed signals for ASR, and using soft-switching to combine them, the proposed method achieves improved ASR performance.
The combination of a deep neural network (DNN) -based speech enhancement (SE) front-end and an automatic speech recognition (ASR) back-end is a widely used approach to implement overlapping speech recognition. However, the SE front-end generates processing artifacts that can degrade the ASR performance. We previously found that such performance degradation can occur even under fully overlapping conditions, depending on the signal-to-interference ratio (SIR) and signal-to-noise ratio (SNR). To mitigate the degradation, we introduced a rule-based method to switch the ASR input between the enhanced and observed signals, which showed promising results. However, the rule's optimality was unclear because it was heuristically designed and based only on SIR and SNR values. In this work, we propose a DNN-based switching method that directly estimates whether ASR will perform better on the enhanced or observed signals. We also introduce soft-switching that computes a weighted sum of the enhanced and observed signals for ASR input, with weights given by the switching model's output posteriors. The proposed learning-based switching showed performance comparable to that of rule-based oracle switching. The soft-switching further improved the ASR performance and achieved a relative character error rate reduction of up to 23 % as compared with the conventional method.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据