| 一种多层子带的噪声语音识别新方法 |
| |
| 引用本文： | 蒋文建,韦岗.一种多层子带的噪声语音识别新方法[J].数据采集与处理,2002,17(1):15-19. |
| |
| 作者姓名： | 蒋文建 韦岗 |
| |
| 作者单位： | 华南理工大学无线电与自动控制研究所,广州,510640 |
| |
| 基金项目： | 国家自然科学基金 (编号 :6 9896 2 4 6 )，广东省“千百十人才培养计划”基金资助项目 |
| |
| 摘 要： | 根据不同尺度子带特征反映语音的不同细节特性，提出一种噪声下的多层子带（MLS）语音识别方法。将语音频谱分成多层多个子带，首先各子带分另单独进行识别，然后将各层各子带识别概率综合起来得到最终识别结果。将新方法应用于TIMIT数据饣E-Set在NoiseX92白噪声和F16噪声下识别实验。实验结果表明，多层子带方法在噪声环境和无噪情况下识别性能都有很大提高。
|
| 关 键 词： | 语音识别 噪声 子带 频谱 语音模型 |
| 文章编号： | 1004-9037(2002)01-0015-05 |
| 修稿时间： | 2001年3月7日 |
A New Method of Combined Multi-Layer Subbands for Noisy Speech Recognition |
| |
| Jiang Wenjian Wei GangResearch Institute of Radio & Automatic Control,South China University of Technology Guangzhou ,P.R.China.A New Method of Combined Multi-Layer Subbands for Noisy Speech Recognition[J].Journal of Data Acquisition & Processing,2002,17(1):15-19. |
| |
| Authors: | Jiang Wenjian Wei GangResearch Institute of Radio & Automatic Control South China University of Technology Guangzhou PRChina |
| |
| Affiliation: | Jiang Wenjian Wei GangResearch Institute of Radio & Automatic Control,South China University of Technology Guangzhou 510640,P.R.China |
| |
| Abstract: | A new method of combined multi-layer subband (MLS) for noisy speech recognition is presented, based on the fact that different scale subbands describe different characteristics of speech. Speech signal is divided into different multi-layer subbands. Each subband is trained and recognized respectively, and probabilities of all subbands are combined to form the final result. The new method is evaluated by a task on TIMIT database of E-Set. White noise and F16 noise of NoiseX92 are added to original speech at different SNRs. Experimental results show that the performance of speech recognition system can be improved by the new method in both noisy and clean environments. |
| |
| Keywords: | speech recognition noise subband |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
