Estimating acoustic speech features in low signal-to-noise ratios using a statistical framework

详细信息    查看全文

• 作者：Philip Harding ; Ben Milner<sup> ; sup><sup>b.milner@uea.ac.uksup>
• 关键词：Voicing ; Fundamental frequency ; Spectral envelope ; Noise adaptation ; Speaker adaptation
• 刊名：Computer Speech & Language
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：42
• 期：Complete
• 页码：1-19
• 全文大小：1259 K
• 卷排序：42

文摘

We propose an integrated statistical framework to estimate acoustic speech features. Speaker and noise adaptation methods are developed and applied to noise-free models. Compared to other methods, the proposal is more accurate particularly at low SNRs.