Browse > Article

A Study on Utterance Verification Using Accumulation of Negative Log-likelihood Ratio  

한명희 (광운대학교 컴퓨터공학과)
이호준 (광운대학교 컴퓨터공학과)
김순협 (광운대학교 컴퓨터공학과)
Abstract
In speech recognition, confidence measuring is to decide whether it can be accepted as the recognized results or not. The confidence is measured by integrating frames into phone and word level. In case of word recognition, the confidence measuring verifies the results of recognition and Out-Of-Vocabulary (OOV). Therefore, the post-processing could improve the performance of recognizer without accepting it as a recognition error. In this paper, we measure the confidence modifying log likelihood ratio (LLR) which was the previous confidence measuring. It accumulates only those which the log likelihood ratio is negative when integrating the confidence to phone level from frame level. When comparing the verification performance for the results of word recognizer with the previous method, the FAR (False Acceptance Ratio) is decreased about 3.49% for the OOV and 15.25% for the recognition error when CAR (Correct Acceptance Ratio) is about 90%.
Keywords
Confidence measure; Utterance verification; Post-processing;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 Speech recognition and utterance verification based on a generalized confidence score /
[ Myoung-Wan Koo.;Chin-Hui Lee;Biing-Hwang Juang ] / Speech and Audio Processing, IEEE Transactions on   ScienceOn
2 반음소 모델링을 이용한 거절기능에 대한 연구 /
[ 김우성;구영완 ] / 한국음향학회지   과학기술학회마을
3 Word and phone level accoustic confidence scoring for speech understanding systems /
[ Kampari ] / Master's thesis, MIT
4 A Hidden Markov Model based keyword recognition system /
[ R.Rose;D.Paul ] / IEEE ICASSP
5 가변어휘 단어 인식에서의 미등록어 거절 알고리즘 성능 비교 /
[ 김기태;문광식;김회린;이영직;정재호 ] / 한국음향학회지   과학기술학회마을