신뢰도 벡터 기반의 다단계 음성인식Multi-stage Speech Recognition Using Confidence Vector
- Other Titles
- Multi-stage Speech Recognition Using Confidence Vector
- Authors
- 전형배; 김승희; 박준; 황규웅; 정훈; 이윤근
- Issue Date
- Sep-2007
- Publisher
- 대한음성학회
- Keywords
- Multi-stage speech recognition; Phoneme recognition; Confidence vector.; Multi-stage speech recognition; Phoneme recognition; Confidence vector.
- Citation
- 말소리, v.1, no.63, pp 113 - 124
- Pages
- 12
- Journal Title
- 말소리
- Volume
- 1
- Number
- 63
- Start Page
- 113
- End Page
- 124
- URI
- https://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/56032
- ISSN
- 1226-1173
- Abstract
- Multi-stage Speech Recognition Using Confidence VectorHyungbae Jeon, Kyuwoong Hwang, Hoon Chung, Seunghi Kim, Jun Park, Yunkeun Lee In this paper, we propose a use of confidence vector as an intermediate input feature for multi-stage based speech recognition architecture to improve recognition accuracy. A multi-stage speech recognition structure is introduced as a method to reduce the computational complexity of the decoding procedure and then accomplish faster speech recognition. Conventional multi-stage speech recognition is usually composed of three stages, acoustic search, lexical search, and acoustic re-scoring. In this paper, we focus on improving the accuracy of the lexical decoding by introducing a confidence vector as an input feature instead of phoneme which was used typically. We take experimental results on 220K Korean Point-of-Interest (POI) domain and the experimental results show that the proposed method contributes on improving accuracy.
- Files in This Item
-
Go to Link
- Appears in
Collections - ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/56032)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.