A robust voice activity detection based on wavelet transform
| Autor: | Mohammad Taghi Manzuri, M. karami, H. tayebi, Kh. Aghajani |
|---|---|
| Rok vydání: | 2008 |
| Předmět: |
Voice activity detection
Computer science business.industry Feature vector Speech recognition Stationary wavelet transform Speech coding Wavelet transform Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing) Pattern recognition Speech processing Speech enhancement Wavelet Computer Science::Sound Artificial intelligence business |
| Zdroj: | 2008 Second International Conference on Electrical Engineering. |
| DOI: | 10.1109/icee.2008.4553895 |
| Popis: | Voice activity detection is an important step in some speech processing systems, such as speech recognition, speech enhancement, noise estimation, speech compression ... etc. In this paper a new voice activity detection algorithm based on wavelet transform is proposed. In this algorithm we use the energy in each sub band, and by two methods we extract feature vector from these values. Experimental results demonstrate advantage over different VAD methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|