Wavelet energy based voice activity detection and adaptive thresholding for efficient speech coding
| Autor: | Shijo M. Joseph, Anto P. Babu |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Discrete wavelet transform
Linguistics and Language Voice activity detection Computer science Speech recognition Speech coding 020207 software engineering 02 engineering and technology PSQM Linear predictive coding Thresholding Language and Linguistics Human-Computer Interaction 030507 speech-language pathology & audiology 03 medical and health sciences Wavelet Codec2 0202 electrical engineering electronic engineering information engineering Computer Vision and Pattern Recognition 0305 other medical science Software |
| Zdroj: | International Journal of Speech Technology. 19:537-550 |
| ISSN: | 1572-8110 1381-2416 |
| Popis: | During the last five decades, extensive researches have been carried out in the field of speech compression, which has resulted in various techniques for speech coding. Researchers have been in full swing for more efficient speech coding and their effort is still continuing in different parts of the world. In this paper we are proposing an alternative method for better speech coding. In the proposed technique we use discrete wavelet transform to decompose the signal and wavelet energy is used to differentiate between active voice region and silence region in the speech signal. Depending upon the region’s status the system, different thresholding strategies have been chosen which leads to a better compression without any loss of speech intelligibility. The proposed method is evaluated in terms of qualitative and quantitative parameters. In this paper we also propose an alternative parameter for MOS values which is here after known as System Recognition Rate. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink