| Paper: | SLP-P11.7 | ||
| Session: | Front-end For Robust Speech Recognition | ||
| Time: | Wednesday, May 17, 16:30 - 18:30 | ||
| Presentation: | Poster | ||
| Topic: | Speech and Spoken Language Processing: End-point detection and barge-in methods | ||
| Title: | A FEATURE FOR VOICE ACTIVITY DETECTION DERIVED FROM SPEECH ANALYSIS WITH THE EXPONENTIAL AUTOREGRESSIVE MODEL | ||
| Authors: | Kentaro Ishizuka, Hiroko Kato, NTT Corporation, Japan | ||
| Abstract: | This paper proposes a feature for voice activity detection (VAD) obtained from a speech signal analysis that uses the exponential autoregressive (ExpAR) model. This model employs exponential terms that depend on the amplitude of observed signals in the AR coefficients part. A parameter in the exponential terms of the ExpAR model called ‘the scaling parameter,’ is directly associated with the degree of nonlinearity of analyzed signals. Based on this property, this parameter is usable as a feature for VAD under noisy conditions. Evaluation experiments showed that our proposed VAD algorithm utilizing only the proposed feature could achieve better performance than two standardized VAD methods, and confirmed the validity of using the proposed feature for VAD. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012