Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | MLSP-P7.3 |
| Session: | Pattern Recognition and Classification II |
| Time: | Friday, May 21, 15:30 - 17:30 |
| Presentation: |
Poster |
| Topic: |
Machine Learning for Signal Processing: Signal detection, Pattern Recognition and Classification |
| Title: |
A SEMI-CONTINUOUS STATE TRANSITION PROBABILITY HMM-BASED VOICE ACTIVITY DETECTION |
| Authors: |
Hisham Othman; University of Ottawa | | |
| | Tyseer Aboulnasr; University of Ottawa | | |
| Abstract: |
In this paper we introduce an efficient Hidden Markov Model-based Voice Activity Detection (VAD) algorithm with time-variant state transition probabilities in the underlying Markov chain. The transition probabilities vary in an exponential charge/discharge scheme and softly are merged with state conditional likelihood into a final VAD decision. Working in the domain of ITU-T G.729 parameters with no additional cost for feature extraction, the proposed algorithm significantly outperforms G.729 Annex B VAD while providing a balanced tradeoff between clipping and false detection errors. The performance compares very favorably with Adaptive MultiRate VAD, phase 2 (AMR2). |
| |
| Back | |