文件名称:20P_ISOLATED
- 所属分类：
- 软件工程
- 资源属性：
- [PDF]
- 上传时间：
- 2015-10-07
- 文件大小：
- 652kb
- 下载次数：
- 0次
- 提 供 者：
- ali k******
- 相关连接：
- 无
- 下载说明：
- 别用迅雷下载，失败请重下，重下不扣分！
介绍说明－－下载内容均来自于网络，请自行研究使用
This paper describes an approach of isolated speech recognition by using the Mel-Scale Frequency
Cepstral Coefficients (MFCC) and Dynamic Time Warping (DTW). Several features are extracted speech signal
of spoken words. An experimental of total five speakers, speaking 10 digits each is collected under
acoustically controlled room is taken. MFCC are extracted speech signal of spoken words. To cope with different
speaking speeds in speech recognition Dynamic Time Warping (DTW) is used. DTW is an algorithm, which is used for
measuring similarity between two sequences, which may vary in time or speed.-This paper describes an approach of isolated speech recognition by using the Mel-Scale Frequency
Cepstral Coefficients (MFCC) and Dynamic Time Warping (DTW). Several features are extracted speech signal
of spoken words. An experimental of total five speakers, speaking 10 digits each is collected under
acoustically controlled room is taken. MFCC are extracted speech signal of spoken words. To cope with different
speaking speeds in speech recognition Dynamic Time Warping (DTW) is used. DTW is an algorithm, which is used for
measuring similarity between two sequences, which may vary in time or speed.
Cepstral Coefficients (MFCC) and Dynamic Time Warping (DTW). Several features are extracted speech signal
of spoken words. An experimental of total five speakers, speaking 10 digits each is collected under
acoustically controlled room is taken. MFCC are extracted speech signal of spoken words. To cope with different
speaking speeds in speech recognition Dynamic Time Warping (DTW) is used. DTW is an algorithm, which is used for
measuring similarity between two sequences, which may vary in time or speed.-This paper describes an approach of isolated speech recognition by using the Mel-Scale Frequency
Cepstral Coefficients (MFCC) and Dynamic Time Warping (DTW). Several features are extracted speech signal
of spoken words. An experimental of total five speakers, speaking 10 digits each is collected under
acoustically controlled room is taken. MFCC are extracted speech signal of spoken words. To cope with different
speaking speeds in speech recognition Dynamic Time Warping (DTW) is used. DTW is an algorithm, which is used for
measuring similarity between two sequences, which may vary in time or speed.
(系统自动生成,下载前可以参看下载内容)
下载文件列表
20P_ISOLATED.pdf