| 一种基于HMM模型的音频场景分析技术 |
| |
| 引用本文： | 魏宇虹,韩纪庆,张磊. 一种基于HMM模型的音频场景分析技术[J]. 计算机工程与应用, 2003, 39(20): 85-86,191 |
| |
| 作者姓名： | 魏宇虹 韩纪庆 张磊 |
| |
| 作者单位： | 哈尔滨工业大学计算机科学与工程系,哈尔滨,150001 |
| |
| 基金项目： | 哈尔滨工业大学跨学科交叉研究基金资助项目(批准号:HIT.MD.200001) |
| |
| 摘 要： | 音频场景分析技术对机器自动感知环境特征具有重要的意义。考虑到Mel频率倒谱系数MFCC(Melfrequen-cycepstralcoefficient)在一定程度上可以模拟人耳的听觉感知特性,因此,提出用MFCC作为音频识别特征,通过隐马尔可夫模型进行音频场景分析的方法,该方法对7种典型场景的识别率在90%以上。
|
| 关 键 词： | 场景分析 音频信号 HMM模型 Mel频率倒谱系数 |
| 文章编号： | 1002-8331-(2003)20-0085-02 |
A Method of Audio Scene Analysis Based on Hidden Markov Model |
| |
| Wei Yuhong Han Jiqing Zhang Lei. A Method of Audio Scene Analysis Based on Hidden Markov Model[J]. Computer Engineering and Applications, 2003, 39(20): 85-86,191 |
| |
| Authors: | Wei Yuhong Han Jiqing Zhang Lei |
| |
| Abstract: | Audio scenes analysis technique plays a very important role for automatic awareness of environmental fea-tures.For the reasons of the auditory characters of human being,the MFCC(Mel frequency cepstral coefficient ),which can represent the auditory characters,is adopted as the feature of audio signal,and a method of audio scene analysis based on HMM is proposed.For typical seven audio scenes,the proposed method gets more than90%recognition rate. |
| |
| Keywords: | Scene Analysis Audio signal HMM Model Mel frequency cepstral coefficient |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
