Virtual acoustic channel expansion based on neural networks for weighted prediction error-based speech dereverberation
- Authors
- Yang, Joon-Young; Chang, Joon Hyuk
- Issue Date
- Oct-2020
- Publisher
- International Speech Communication Association
- Keywords
- Multi-channel linear prediction; Neural network; Speech dereverberation; Weighted prediction error
- Citation
- Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, v.2020, no.October, pp.3930 - 3934
- Indexed
- SCOPUS
- Journal Title
- Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
- Volume
- 2020
- Number
- October
- Start Page
- 3930
- End Page
- 3934
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/3662
- DOI
- 10.21437/Interspeech.2020-1553
- ISSN
- 2308-457X
- Abstract
- In this study, we propose a neural-network-based virtual acoustic channel expansion (VACE) framework for weighted prediction error (WPE)-based speech dereverberation. Specifically, for the situation in which only a single microphone observation is available, we aim to build a neural network capable of generating a virtual signal that can be exploited as the secondary input for the dual-channel WPE algorithm, thus making its dereverberation performance superior to the single-channel WPE. To implement the VACE-WPE, the neural network for the VACE is initialized and integrated to the pre-trained neural WPE algorithm. The entire system is then trained in a supervised manner to output a dereverberated signal that is close to the oracle early arriving speech. Experimental results show that the proposed VACE-WPE method outperforms the single-channel WPE in a real room impulse response shortening task.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 융합전자공학부 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.