Manuel Gorriz, Juan and Ramirez, Javier and Lang, Elmar W. and Puntonet, Arlos G. (2008) Jointly Gaussian PDF-Based Likelihood Ratio Test for Voice Activity Detection. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 16 (8). pp. 1565-1578. ISSN 1558-7916, 1558-7924
Full text not available from this repository. (Request a copy)Abstract
This paper presents a novel voice activity detector (VAD) for improving speech detection robustness in noisy environments and the performance of speech recognition systems in real-time applications. The algorithm is based on a generalized complex Gaussian (GCG) observation model and defines an optimal likelihood ratio test (LRT) involving multiple and correlated observations (MCO) based on jointly Gaussian probability distribution functions (jGpdf). An extensive analysis of the proposed methodology for a low dimensional observation model demonstrates 1) the improved robustness of the proposed approach by means of a clear reduction of the classification error as the number of observations is increased, and 2) the tradeoff between the number of observations and the detection performance. The proposed strategy is also compared to different VAD methods including the G.729, AMR, and AFE standards, as well as other recently reported algorithms showing a sustained advantage in speech/nonspeech detection accuracy and speech recognition performance.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | SPEECH RECOGNITION; NOISE; LRT; INFORMATION; MODEL; VAD; Generalized complex Gaussian (GCG) probability distribution function; robust speech recognition; voice activity detection (VAD) |
| Subjects: | 500 Science > 570 Life sciences |
| Divisions: | Biology, Preclinical Medicine > Institut für Biophysik und physikalische Biochemie > Prof. Dr. Elmar Lang |
| Depositing User: | Dr. Gernot Deinzer |
| Date Deposited: | 19 Oct 2020 12:51 |
| Last Modified: | 19 Oct 2020 12:51 |
| URI: | https://pred.uni-regensburg.de/id/eprint/30103 |
Actions (login required)
 |
View Item |
