摘要
An improved non-intrusive objective speech quality evaluation method is proposed based on Fuzzy Gaussian Mixture Model (FGMM) and Fuzzy Neural Network (FNN). The degraded speech is separated into three classes (unvoiced, voiced and silence), then for each class the consistency measurement between Perceptual Linear Predictive (PLP) features of the degraded speech and the pre-trained FGMM reference model is calculated and mapped to an objective speech quality score using FNN mapping method. The proposed method performs better than the previous work using GMM and ITU-T P.563 under the test conditions used in this paper.
| 源语言 | 英语 |
|---|---|
| 主期刊名 | Proceedings - 2010 3rd International Congress on Image and Signal Processing, CISP 2010 |
| 页 | 3495-3499 |
| 页数 | 5 |
| DOI | |
| 出版状态 | 已出版 - 2010 |
| 活动 | 2010 3rd International Congress on Image and Signal Processing, CISP 2010 - Yantai, 中国 期限: 16 10月 2010 → 18 10月 2010 |
出版系列
| 姓名 | Proceedings - 2010 3rd International Congress on Image and Signal Processing, CISP 2010 |
|---|---|
| 卷 | 7 |
会议
| 会议 | 2010 3rd International Congress on Image and Signal Processing, CISP 2010 |
|---|---|
| 国家/地区 | 中国 |
| 市 | Yantai |
| 时期 | 16/10/10 → 18/10/10 |
指纹
探究 'An improved non-intrusive objective speech quality evaluation based on FGMM and FNN' 的科研主题。它们共同构成独一无二的指纹。引用此
Wang, J., Zhang, Y., Song, Y., Zhao, S., & Kuang, J. (2010). An improved non-intrusive objective speech quality evaluation based on FGMM and FNN. 在 Proceedings - 2010 3rd International Congress on Image and Signal Processing, CISP 2010 (页码 3495-3499). 文章 5646757 (Proceedings - 2010 3rd International Congress on Image and Signal Processing, CISP 2010; 卷 7). https://doi.org/10.1109/CISP.2010.5646757