Presentation 2005/12/15
Model-Based Wiener Filter for Noise Robust Speech Recognition
Takayuki ARAKAWA, Masanori TSUJIKAWA, Ryosuke ISOTANI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a new approach for noise robust speech recognition, Model-Based Wiener Filter. This method takes three steps to estimate clean speech signals from noisy speech signals. The first step is the spectral subtraction (SS). Since the SS averagely subtracts noise components, the estimated speech signals often include distortion. In the second step, the distortion caused by SS is reduced using the minimum mean square error estimation for a Gaussian mixture model. In the final step, the Wiener Filtering is performed with the decision-directed method. Experiments are conducted using the AURORA2-J database. The results show that the proposed method performs as well as the ETSI advanced front-end in average and the variation range of the recognition accuracy according to the kind of noise is about one third, which demonstrates the robustness of the proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # NLC2005-84,SP2005-117
Date of Issue

Conference Information
Committee NLC
Conference Date 2005/12/15(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 JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Model-Based Wiener Filter for Noise Robust Speech Recognition
Sub Title (in English)
Keyword(1)
1st Author's Name Takayuki ARAKAWA
1st Author's Affiliation NEC Media and Information Research Laboratories()
2nd Author's Name Masanori TSUJIKAWA
2nd Author's Affiliation NEC Media and Information Research Laboratories
3rd Author's Name Ryosuke ISOTANI
3rd Author's Affiliation NEC Media and Information Research Laboratories
Date 2005/12/15
Paper # NLC2005-84,SP2005-117
Volume (vol) vol.105
Number (no) 494
Page pp.pp.-
#Pages 2
Date of Issue