| 基于CMN和PMC算法的语音增强失真补偿方法研究 |
| |
| 引用本文： | 苗玉杰,刘雪飞,张晓敏.基于CMN和PMC算法的语音增强失真补偿方法研究[J].微电子学与计算机,2011,28(6). |
| |
| 作者姓名： | 苗玉杰 刘雪飞 张晓敏 |
| |
| 作者单位： | 1. 中国环境管理干部学院,河北,秦皇岛,066004
2. 秦皇岛职业技术学院,河北,秦皇岛,066004 |
| |
| 基金项目： | 河北省科技厅科学技术研究与发展计划项目 |
| |
| 摘 要： | 语音增强技术在低信噪比情况下,由于语音增强带来的失真使得系统的识别性能严重下降.因此提出一种结合特征空间的倒谱均值归一化算法(CMN)和模型空间的并行模型合并算法(PMC)的语音增强失真补偿技术.实验结果表明,该方法有效提高了低信噪比情况下的语音信号识别率.
|
| 关 键 词： | 语音增强 倒谱均值归一化 并行模型合并 |
Compensation of Speech Enhancement Distortion with Combination of CMN and PMC |
| |
| MIAO Yue-jie,LIU Xue-fei,ZHANG Xiao-min.Compensation of Speech Enhancement Distortion with Combination of CMN and PMC[J].Microelectronics & Computer,2011,28(6). |
| |
| Authors: | MIAO Yue-jie LIU Xue-fei ZHANG Xiao-min |
| |
| Affiliation: | MIAO Yue-jie1,LIU Xue-fei1,ZHANG Xiao-min2(1 Environment Management College of China,Qinhuangdao 066004,China,2 Vocational Technology College of Qinhuangdao,China) |
| |
| Abstract: | The performance of speech recognition systems degrades severely when speech enhancement technique is applied under low the SNR ratio because of the distortion induced by speech enhancement.This paper presents a Parallel Model Combination(PMC) in model space and Cepstral Mean Normalization(CMN) in characteristic space to compensate the distortion.Results are presented that demonstrate the effective combination of robust methods in different space can significantly improve the recognition rate. |
| |
| Keywords: | speech enhancement Cepstral Mean Normalization(CMN) Parallel Model Combination(PMC) |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
