상세정보
학술지
신뢰도 벡터 기반의 다단계 음성 인식
Cited - time in 
Download 16 time
Share 
Download 16 time
Share
- 발행일
- 200709
- 출처
- 대한음성학회지 : 말소리, v.63, pp.113-124
- ISSN
- 1226-1173
- 출판사
- 대한음성학회
- 초록
- 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.
- KSP 제안 키워드
- Computational complexity, Improving accuracy, Intermediate input, Multi-stage, Point of interest, Recognition Accuracy, speech recognition