상세정보
학술지
다양한 신뢰도 척도를 이용한 SVM 기반 발화 검증 연구
Cited - time in 
Download 10 time
Share 
Download 10 time
Share
- 저자
- 권석봉, 김희린, 강점자, 구명완, 류창선
- 발행일
- 200612
- 출처
- 대한음성학회지 : 말소리, v.1 no.60, pp.165-180
- ISSN
- 1226-1173
- 출판사
- 대한음성학회
- 협약과제
- 07MW1700, 신성장동력산업용 대용량 대화형 분산 처리 음성인터페이스 기술개발, 이윤근
- 초록
- SVM-based Utterance Verification Using Various Confidence MeasuresSuk-bong Kwon, Hoirin Kim, Jeomja Kang, Myong-Wan Koo, Chang-Sun RyuIn this paper, we present several confidence measures (CM) for speech recognition systems to evaluate the reliability of recognition results. We propose heuristic CMs such as mean log-likelihood score, N-best word log-likelihood ratio, likelihood sequence fluctuation and likelihood ratio testing(LRT)-based CMs using several types of anti-models. Furthermore, we propose new algorithms to add weighting terms on phone-level log-likelihood ratio to merge word-level log-likelihood ratios. These weighting terms are computed from the distance between acoustic models and knowledge-based phoneme classifications. LRT-based CMs show better performance than heuristic CMs excessively, and LRT-based CMs using phonetic information show that the relative reduction in equal error rate ranges between 8 ~ 13% compared to the baseline LRT-based CMs. We use the support vector machine to fuse several CMs and improve the performance of utterance verification. From our experiments, we know that selection of CMs with low correlation is more effective than CMs with high correlation.
- KSP 제안 키워드
- Confidence measure, Knowledge-based, Relative reduction, Support VectorMachine(SVM), acoustic model, equal error rate, log likelihood ratio(LLR), low correlation, speech recognition, word-level