| 利用语音的频谱空间特征进行汉语抗噪语音识别的方法 |
| |
| 引用本文： | 张永锋,田勇,张阳.利用语音的频谱空间特征进行汉语抗噪语音识别的方法[J].声学技术,2015,34(1):51-53. |
| |
| 作者姓名： | 张永锋 田勇 张阳 |
| |
| 作者单位： | 大连东软信息学院电子工程系, 辽宁大连 116023;大连东软信息学院电子工程系, 辽宁大连 116023;大连东软信息学院电子工程系, 辽宁大连 116023 |
| |
| 摘 要： | 抗噪连续语音识别是当前汉语连续语音识别的重要研究领域。采用通过度量连续语音帧之间频谱的稳定性,将连续语音切分成份,再将切分结果(无论时间长短)变换为与时间无关的大小固定的频谱空间特征,通过与模板库进行比较实现语音识别。新的频谱空间特征,与语音时长无关,同时表现出较好的抗噪声能力。在特定人连续语音识别测试系统中,取得了不错的识别效果。
|
| 关 键 词： | 语音特征 连续语音识别 抗噪语音识别 |
| 收稿时间： | 2013/3/28 0:00:00 |
| 修稿时间： | 2013/6/29 0:00:00 |
Spatial characteristics of speech spectrum for robust speech recognition |
| |
| ZHANG Yong-feng,TIAN Yong and ZHANG Yang.Spatial characteristics of speech spectrum for robust speech recognition[J].Technical Acoustics,2015,34(1):51-53. |
| |
| Authors: | ZHANG Yong-feng TIAN Yong and ZHANG Yang |
| |
| Affiliation: | Dept. of Electronic Engineering, DalianNeusoft Institute of Information, Dalian 60, Liaoning, China;Dept. of Electronic Engineering, DalianNeusoft Institute of Information, Dalian 60, Liaoning, China;Dept. of Electronic Engineering, DalianNeusoft Institute of Information, Dalian 60, Liaoning, China |
| |
| Abstract: | The anti-noise continuous speech recognition is an important research topic of current Chinese continuous speech recognition. In this paper, by measuring the stability of the frequency spectrum between the continuous speech frames, speech signal can be segmented, and then these segmentations regardless of the length of time are transformed into time-independent and size-fixed spatial characteristics of speech spectrum. By comparing to speech template, the speech recognition results are obtained. The new spatial characteristics of speech spectrum are independent of speech length, and show better immunity to noise. In a specific continuous speech recognition testing system, favorable recognition result is obtained. |
| |
| Keywords: | speech characteristics continuous speech recognition anti-noise speech recognition |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《声学技术》浏览原始摘要信息 |
|
点击此处可从《声学技术》下载全文 |
|
