Presentation | 2009-12-22 Voice activity detection using conditional random fields with multiple features Akira SAITO, Yoshihiko NANKAKU, Akinobu LEE, Keiichi TOKUDA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Voice Activity Detection(VAD)which is a technique to distinguish between speech and non-speech is used in noisy environments and an important component in many real-world speech applications. In this paper, we propose a VAD algorithm based on Conditional Random Fields(CRF)with multiple features, e.g., amplitude, f_0 and the likelihood of GMMs. In the proposed method, the relation between input features and output speech/non-speech labels is represented by feature functions, and the posterior probability of output labels is directly modeled by the weighted sum of the feature functions. By estimating appropriate weight parameters, effective features are automatically selected for improving the performance of VAD. Experimental results on CENSREC-1-C database show that the proposed method can decrease error rates by using conditional random fields. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Voice activity detection / Conditional random fields / Gaussian mixture model |
Paper # | NLC2009-18,SP2009-82 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 2009/12/14(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) | Voice activity detection using conditional random fields with multiple features |
Sub Title (in English) | |
Keyword(1) | Voice activity detection |
Keyword(2) | Conditional random fields |
Keyword(3) | Gaussian mixture model |
1st Author's Name | Akira SAITO |
1st Author's Affiliation | Department of Computer Science and Engineering, Nagoya Institute of Technology() |
2nd Author's Name | Yoshihiko NANKAKU |
2nd Author's Affiliation | Department of Computer Science and Engineering, Nagoya Institute of Technology |
3rd Author's Name | Akinobu LEE |
3rd Author's Affiliation | Department of Computer Science and Engineering, Nagoya Institute of Technology |
4th Author's Name | Keiichi TOKUDA |
4th Author's Affiliation | Department of Computer Science and Engineering, Nagoya Institute of Technology |
Date | 2009-12-22 |
Paper # | NLC2009-18,SP2009-82 |
Volume (vol) | vol.109 |
Number (no) | 355 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |