Spectro-temporal Smoothed Auditory Spectra for Robust Speaker Identification
碩士 === 國立交通大學 === 電信工程研究所 === 98 === The performance of conventional speaker recognition systems is severely compromised by interference, such as additive or convolutional noises. High-level information of the speaker is considered more robust cues for recognizing speakers. This paper proposes an au...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | en_US |
| Published: |
2010
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/93426071838577958845 |