| 一种基于分带谱熵和谱能量的语音端点检测算法 |
| |
| 引用本文： | 李如玮, 鲍长春. 一种基于分带谱熵和谱能量的语音端点检测算法[J]. 北京工业大学学报, 2007, 33(9): 920-924. |
| |
| 作者姓名： | 李如玮 鲍长春 |
| |
| 作者单位： | 1.北京工业大学 电子信息与控制工程学院, 北京 100022 |
| |
| 基金项目： | 北京市教委科技发展计划项目，北京工业大学校科研和教改项目，北京市跨世纪优秀人才培养计划 |
| |
| 摘 要： | 语音端点检测的精确度直接影响语音识别的准确度.在噪声环境下,语音端点检测很困难.信噪比下降,语音端点检测的正确率也随之下降,同时,噪声类型的变化影响端点检测的正确率.为此,提出了一种改进的、适合在电话语音城市名识别系统中应用的端点检测算法,并结合分带谱熵和谱能量形成了一个新的特征参数集,利用该参数集进行端点检测,弥补了分别采用分带谱熵和谱能量进行端点检测的缺陷,提高了检测性能.
|
| 关 键 词： | 语音处理 语音识别 谱分析 端点检测 分带谱熵 |
| 文章编号： | 0254-0037（2007）09-0920-05 |
| 收稿时间： | 2006-09-04 |
| 修稿时间： | 2006-09-04 |
A Speech Endpoint Detection Algorithm Based on the Band-partitioning Spectral Entropy and Spectral Energy |
| |
| LI Ru-wei, BAO Chang-chun. A Speech Endpoint Detection Algorithm Based on the Band-partitioning Spectral Entropy and Spectral Energy[J]. Journal of Beijing University of Technology, 2007, 33(9): 920-924. |
| |
| Authors: | LI Ru-wei BAO Chang-chun |
| |
| Affiliation: | 1.College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100022, China |
| |
| Abstract: | The accuracy of speech recognition directly depends on accurate endpoint detection.Endpoint detec- tion is a very difficult task in the noise environment.It will be degraded with the decrease of SNR and differ- ent noise affects the accuracy of speech recognition.As a result,this paper proposed an endpoint detection ap- proach which is applicable to the telephone speech recognition system for city's name.The approach inte- grates band-partitioning spectral entropy and spectral energy to form a set of new feature parameters that can compensating the drawback of entropy and energy so that the performance of the detection is improved. |
| |
| Keywords: | speech processing speech recognition spectrum analysis endpoint detection band-partitioning spectral entropy |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《北京工业大学学报》浏览原始摘要信息 |
|
点击此处可从《北京工业大学学报》下载全文 |
