| 氦语音增强算法的研究 |
| |
| 引用本文： | 成少锋,李双田,邓昊.氦语音增强算法的研究[J].应用声学,2004,23(2):15-19. |
| |
| 作者姓名： | 成少锋 李双田 邓昊 |
| |
| 作者单位： | 中国科学院声学研究所,北京,100080 |
| |
| 基金项目： | 中国科学院声学研究所知识创新工程前瞻性项目基金资助 |
| |
| 摘 要： | 当潜水员深海作业时，由于生理方面的原因，需要以氦氧混合气体为呼吸介质替代空气，但这时会出现所谓的“氦语音”现象，语音产生很大畸变，清晰度极低。本文给出了氦语音的基本变化规律，介绍了两种分别基于短时傅立叶变换和线性预测模型的增强算法。我们的实验结果表明，两种算法均能显著校正氦语音，提高清晰度。
|
| 关 键 词： | 氦语音增强算法 深海作业 语音畸变 短时傅立叶变换 |
A study on the algorithm of helium speech enhancement |
| |
| CHENG Shao-Feng,LI Shuang-Tian and DENG Hao.A study on the algorithm of helium speech enhancement[J].Applied Acoustics,2004,23(2):15-19. |
| |
| Authors: | CHENG Shao-Feng LI Shuang-Tian and DENG Hao |
| |
| Institution: | Institute of Acoustics, Chinese Academy of Sciences, Beijing 100080;Institute of Acoustics, Chinese Academy of Sciences, Beijing 100080;Institute of Acoustics, Chinese Academy of Sciences, Beijing 100080 |
| |
| Abstract: | When divers work at deep sea, for physiological reasons, they must breathe helium-oxygen mixed atmosphere in place of air. Unfortunately, the resulting helium speech is distorted very much, and nearly unintelligible. This paper describes the essential law of helium speech transformation, presents two enhancement algorithms based respectively on short-term fourier transform and linear prediction. Our experimental results show that both algorithms can correct helium speech and the intelligibility is enhanced greatly. |
| |
| Keywords: | Helium speech Short-term fourier transform Linear prediction |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《应用声学》浏览原始摘要信息 |
| 点击此处可从《应用声学》下载免费的PDF全文 |
