Browse > Article

A Study on Trend Sharing in Segmental-feature HMM  

윤영선 (한남대학교 정보통신.멀티미디어공학부)
Abstract
In this paper, we propose the reduction method of the number of parameters in the segmental-feature HMM using trend quantization method. The proposed method shares the trend information of the polynomial trajectories by quantization. The trajectory is obtained by the sequence of feature vectors of speech signals and can be divided by trend and location information. The trend indicates the variation of consequent frame features, while the location points to the positional difference of the trajectories. Since the trend occupies the large portion of SFHMM, if the trend is shared, the number of parameters maybe decreases. To exploit the proposed system the experiments are performed on TIMIT corpus. The experimental results show that the performance of the proposed system is roughly similar to that of previous system. Therefore, the proposed system can be considered one of parameter reduction method.
Keywords
Segmental-feature HMM; Reduction method of number of parameters; Segmental feature; Speech recognition;
Citations & Related Records
Times Cited By KSCI : 3  (Citation Analysis)
연도 인용수 순위
1 모수적 궤적 기반의 분절 HMM을 이용한 연속음성 인식 /
[ 윤영선;오영환 ] / 한국음향학회지   과학기술학회마을
2 분절 특징 HMM을 이용한 영어 음소 인식 /
[ 윤영선 ] / 한국정보과학회지   과학기술학회마을
3 분절 특징 HMM의 매개변수 수의 감소에 관한 연구 /
[ 윤영선;오영환 ] / 한국음향학회지   과학기술학회마을
4 A segmental speech model with application word spotting /
[ H.Gish;K.Ng ] / Proc. of Int. Conf. on Acoustics, Speech and Signal Proc.
5 Segmental hidden markov models /
[ M.J.F.Gales;S.J.Young ] / Proceedings of European Conference on Speech Communication and Technology
6 Speaker-independent isolated word recognition using dynamic features of speech spectrum /
[ S.Furui ] / IEEE Trans. on Acoustics, Speech and Signal Processing   DOI
7 Parametric trajectory models for speech recognition /
[ H.Gish;K.Ng ] / Proceedings of International Conference on Spoken Language Processing
8 A generalized hidden markov model with state conditioned trend functions of time for the speech signal /
[ L.Deng ] / Signal Processing   DOI   ScienceOn
9 Speech recognition using hidden markov models with polynomial regression functions as non-stationary states /
[ L.Deng;M.Aksmanovic;D.Sun;J.Wu ] / IEEE Trans. on Speech and Audio Processing   DOI   ScienceOn
10 From HMMs to segment models: A unified view of stochastic modeling for speech recognition /
[ M.Ostendorf;V.Digalakis;O.A.Kimball ] / IEEE Tr. on Speech and Audio Processing   DOI   ScienceOn
11 Probabilistic trajectory segmental HMMs /
[ W.J.Holmes;M.J.Russell ] / Computer Speech and Language   DOI   ScienceOn