Multichannel signal separation for cocktail party speech recognition: a dynamic recurrent network
SCIE
SCOPUS
- Title
- Multichannel signal separation for cocktail party speech recognition: a dynamic recurrent network
- Authors
- Choi, S; Hong, H; Glotin, H; Berthommier, F
- Date Issued
- 2002-12
- Publisher
- ELSEVIER SCIENCE BV
- Abstract
- This paper addresses a method of multichannel signal separation (MSS) with its application to cocktail party speech recognition. First, we present a fundamental principle for multichannel signal separation which uses the spatial independence of located sources as well as the temporal dependence of speech signals. Second, for practical implementation of the signal separation filter, we consider a dynamic recurrent network and develop a simple new learning algorithm. The performance of the proposed method is evaluated in terms of word recognition error rate (WER) in a large speech recognition experiment. The results show that our proposed method dramatically improves the word recognition performance in the case of two simultaneous speech inputs, and that a timing effect is involved in the segregation process. (C) 2002 Elsevier Science B.V. All rights reserved.
- Keywords
- blind signal separation; cocktail party problem; speech recognition; dynamic recurrent networks; multichannel signal separation; BLIND SEPARATION
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/18739
- DOI
- 10.1016/S0925-2312(02)00522-2
- ISSN
- 0925-2312
- Article Type
- Article
- Citation
- NEUROCOMPUTING, vol. 49, page. 299 - 314, 2002-12
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.