Presentation 2004/12/13
Speech recognition method based on trajectories generated by Kalman filters
Yasuhiro MINAMI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We previously proposed a speech recognition method using trajectory models that unfortunately had some difficulty treating HMMs with Gaussian mixture distributions. Therefore, this paper proposes a new trajectory generation method that extends the use of HMM-trajectory with Gaussian mixture HMMs, generates linear dynamic system models from the HMMs, and then performs switching Kalman filters to generate smooth trajectory with them. Experiments show that the method generates smooth trajectories.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) HMM / Kalman filter / switching Kalman filter / trajectory
Paper # NLC2004-49,SP2004-89
Date of Issue

Conference Information
Committee NLC
Conference Date 2004/12/13(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Natural Language Understanding and Models of Communication (NLC)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Speech recognition method based on trajectories generated by Kalman filters
Sub Title (in English)
Keyword(1) HMM
Keyword(2) Kalman filter
Keyword(3) switching Kalman filter
Keyword(4) trajectory
1st Author's Name Yasuhiro MINAMI
1st Author's Affiliation NTT communication science laboratories, NTT corporation()
Date 2004/12/13
Paper # NLC2004-49,SP2004-89
Volume (vol) vol.104
Number (no) 538
Page pp.pp.-
#Pages 6
Date of Issue