Presentation | 2007/12/13 Evaluation of Hands-free Speech Recognition Algorithm using Decoding Voice Activity Detection based on Acoustic and Language Models Hiroyuki SAKAI, Tobias CINCAREK, Hiromichi KAWANAMI, Hiroshi SARUWATARI, Kiyohiro SHIKANO, Akinobu LEE, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Introduction of hands-free interface into speech recognition (SR) systems is expected for natural iteraction between humans and spoken dialogue robots. In hands-free SR system, Signal-to-Noise Ratio (SNR) of input signal becomes worse because of background noise in real-environment and other reasons. This will cause degradation in recognition performance when using conventional Voice Activity Detection (VAD). In this paper, we evaluate hands-free SR algorithm using decoding VAD based on acoustic and language models for robust VAD in noisy environment. We performed experiment for comparing proposed and conventional VAD method, for example, based on amplitude power, statistical model and GMM. And, we evaluate effectiveness of the proposed method. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Voice Activity Detection (VAD) by decoding based on Acoustic Model and Language Model / Hands-Free speech recognition / Real-environment spoken dialogue robot |
Paper # | NLC2007-35,SP2007-98 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 2007/12/13(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 | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Evaluation of Hands-free Speech Recognition Algorithm using Decoding Voice Activity Detection based on Acoustic and Language Models |
Sub Title (in English) | |
Keyword(1) | Voice Activity Detection (VAD) by decoding based on Acoustic Model and Language Model |
Keyword(2) | Hands-Free speech recognition |
Keyword(3) | Real-environment spoken dialogue robot |
1st Author's Name | Hiroyuki SAKAI |
1st Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology() |
2nd Author's Name | Tobias CINCAREK |
2nd Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
3rd Author's Name | Hiromichi KAWANAMI |
3rd Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
4th Author's Name | Hiroshi SARUWATARI |
4th Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
5th Author's Name | Kiyohiro SHIKANO |
5th Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
6th Author's Name | Akinobu LEE |
6th Author's Affiliation | Nagoya Institute of Technology |
Date | 2007/12/13 |
Paper # | NLC2007-35,SP2007-98 |
Volume (vol) | vol.107 |
Number (no) | 405 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |