Multilingual Approach to Joint Speech and Accent Recognition with DNN-HMM Framework
This addresses the challenge of recognizing accents alongside speech for multilingual ASR systems, though it is incremental as it builds on existing DNN-HMM methods.
The paper tackles the problem of joint speech and accent recognition in English by treating different accents as separate languages within a DNN-HMM framework, achieving word error rates (WERs) close to conventional ASR systems and desired accent recognition accuracy on an 8-accent dataset.
Human can recognize speech, as well as the peculiar accent of the speech simultaneously. However, present state-of-the-art ASR system can rarely do that. In this paper, we propose a multilingual approach to recognizing English speech, and related accent that speaker conveys using DNN-HMM framework. Specifically, we assume different accents of English as different languages. We then merge them together and train a multilingual ASR system. During decoding, we conduct two experiments. One is a monolingual ASR-based decoding, with the accent information embedded at phone level, realizing word-based accent recognition (AR), and the other is a multilingual ASR-based decoding, realizing an approximated utterance-based AR. Experimental results on an 8-accent English speech recognition show both methods can yield WERs close to the conventional ASR systems that completely ignore the accent, as well as desired AR accuracy. Besides, we conduct extensive analysis for the proposed method, such as transfer learning without-domain data exploitation, cross-accent recognition confusion, as well as characteristics of accented-word.