Browse > Article

Improvement of Domain-specific Keyword Spotting Performance Using Hybrid Confidence Measure  

이경록 (전남대학교 전자공학과 & RRC HECS)
서현철 (전남대학교 전자공학과 & RRC HECS)
최승호 (동신대학교 정보통신공학과)
최승호 (서울산업대학교 전자공학과)
김진영 (전남대학교 전자공학과 & RRC HECS)
Abstract
In this paper, we proposed ACM (Anti-filler confidence measure) to compensate shortcoming of conventional RLJ-CM (RLJ-CM) and NCM (normalized CM), and integrated proposed ACM and conventional NCM using HCM (hybrid CM). Proposed ACM analyzes that FA (false acceptance) happens by the construction method of anti-phone model, and presumed phoneme sequence in actuality using phoneme recognizer to compensate this. We defined this as anti-phone model and used in confidence measure calculation. Analyzing feature of two confidences measure, conventional NCM shows good performance to FR (false rejection) and proposed ACM shows good performance in FA. This shows that feature of each other are complementary. Use these feature, we integrated two confidence measures using weighting vector α And defined this as HCM. In MDR (missed detection rate) 10% neighborhood, HCM is 0.219 FA/KW/HR (false alarm/keyword/hour). This is that Performance improves 22% than used conventional NCM individually.
Keywords
Hybrid confidence measure; Anti-filler confidence measure; Normalized confidence measure; Postprocessing; Keyword spotting;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 기변어휘 단어 인식에서의 미등록어 거절 알고리즘 성능 비교 /
[ 김기태;문광식;김회린;이영직;정재호 ] / 한국음향학회지   과학기술학회마을
2 정규화 신뢰도를 이용한 핵심어 검출 성능 향상 /
[ 김 철;이경록;김진영;최승호;최승호 ] / 한국음향학회지   과학기술학회마을
3 Token Passing : a simple conceptual model for connected speech recognition systems /
[ S.J.Young;N.H.Russell;J.H.S.Thornton ] / Technical report of Cambridge university engineering department, TR 38
4 Discriminative utterance verification using minimum string verification error (MSVE) training /
[ M.G.Rahim;C.H.Lee;B.H.Juang;W.Chou ] / Proc. of ICASSP 96
5 Phonetic-based word spotter: Various configurations and application to event spotting /
[ P.Jeanrenaud;K.Ng;J.R.Siu;M.Rohlicek;H.Gish ] / Proc. of Eurospeech