Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

A Speaker-Dependent Approach to Single-Channel Joint Speech Separation and Acoustic Modeling Based on Deep Neural Networks for Robust Recognition of Multi-Talker Speech

A Speaker-Dependent Approach to Single-Channel Joint Speech Separation and Acoustic Modeling... We propose a novel speaker-dependent (SD) multi-condition (MC) training approach to joint learning of deep neural networks (DNNs) of acoustic models and an explicit speech separation structure for recognition of multi-talker mixed speech in a single-channel setting. First, an MC acoustic modeling framework is established to train a SD-DNN model in multi-talker scenarios. Such a recognizer significantly reduces the decoding complexity and improves the recognition accuracy over those using speaker-independent DNN models with a complicated joint decoding structure assuming the speaker identities in mixed speech are known. In addition, a SD regression DNN for mapping the acoustic features of mixed speech to the speech features of a target speaker is jointly trained with the SD-DNN based acoustic models. Experimental results on Speech Separation Challenge (SSC) small-vocabulary recognition show that the proposed approach under multi-condition training achieves an average word error rate (WER) of 3.8%, yielding a relative WER reduction of 65.1% from a top performance, DNN-based pre-processing only approach we proposed earlier under clean-condition training (Tu et al. 2016). Furthermore, the proposed joint training DNN framework generates a relative WER reduction of 13.2% from state-of-the-art systems under multi-condition training. Finally, the effectiveness of the proposed approach is also verified on the Wall Street Journal (WSJ0) task with medium-vocabulary continuous speech recognition in a simulated multi-talker setting. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Signal Processing Systems Springer Journals

A Speaker-Dependent Approach to Single-Channel Joint Speech Separation and Acoustic Modeling Based on Deep Neural Networks for Robust Recognition of Multi-Talker Speech

Download PDF
11 pages

Loading next page...
 
/lp/springer_journal/a-speaker-dependent-approach-to-single-channel-joint-speech-separation-TtcGa420FX

References (33)

Publisher
Springer Journals
Copyright
Copyright © 2017 by Springer Science+Business Media, LLC
Subject
Engineering; Signal,Image and Speech Processing; Circuits and Systems; Electrical Engineering; Image Processing and Computer Vision; Pattern Recognition; Computer Imaging, Vision, Pattern Recognition and Graphics
ISSN
1939-8018
eISSN
1939-8115
DOI
10.1007/s11265-017-1295-x
Publisher site
See Article on Publisher Site

Abstract

We propose a novel speaker-dependent (SD) multi-condition (MC) training approach to joint learning of deep neural networks (DNNs) of acoustic models and an explicit speech separation structure for recognition of multi-talker mixed speech in a single-channel setting. First, an MC acoustic modeling framework is established to train a SD-DNN model in multi-talker scenarios. Such a recognizer significantly reduces the decoding complexity and improves the recognition accuracy over those using speaker-independent DNN models with a complicated joint decoding structure assuming the speaker identities in mixed speech are known. In addition, a SD regression DNN for mapping the acoustic features of mixed speech to the speech features of a target speaker is jointly trained with the SD-DNN based acoustic models. Experimental results on Speech Separation Challenge (SSC) small-vocabulary recognition show that the proposed approach under multi-condition training achieves an average word error rate (WER) of 3.8%, yielding a relative WER reduction of 65.1% from a top performance, DNN-based pre-processing only approach we proposed earlier under clean-condition training (Tu et al. 2016). Furthermore, the proposed joint training DNN framework generates a relative WER reduction of 13.2% from state-of-the-art systems under multi-condition training. Finally, the effectiveness of the proposed approach is also verified on the Wall Street Journal (WSJ0) task with medium-vocabulary continuous speech recognition in a simulated multi-talker setting.

Journal

Journal of Signal Processing Systems – Springer Journals

Published: Oct 4, 2017

There are no references for this article.