搜索资源列表
EndPoint
- 一个语音信号端点检测的程序,算法可能需要根据具体的应用调整一些参数。请使用者自己调整,根据不同的噪声环境。
基于LPC美尔倒谱特征的带噪语音端点检测
- 基于LPC美尔倒谱特征的带噪语音端点检测.rar格式为vip-America Fall Cepstral Noisy voice endpoint detection. Rar format vip
基于倒谱特征的带噪语音端点检测
- 基于倒谱特征的带噪语音端点检测.rar格式为vip-based Cepstral Noisy voice endpoint detection. Rar format vip
基于有限状态机的汉语数字语音端点检测
- 基于有限状态机的汉语数字语音端点检测.rar.rar格式为vip-based on the finite state machine language digital voice endpoint detection. Rar.rar format vip
基于熵函数的语音端点检测方法
- 基于熵函数的语音端点检测方法.rar格式为vip-voice endpoint detection methods. Rar format vip
duandianjiance
- 基于支持向量机的语音信号端点检测,主要是去掉首位的噪声。-Voice signal endpoint detection based on support vector machines, mainly to get rid of the first noise.
Spectral_Entropy
- 连续语音端点检测,短时能量、过零率以及谱熵相结合,健壮性好,识别率高。阈值为自适应,可适合情况下语音端点检测。-Continuous speech endpoint detection, short-term energy, zero-crossing rate and spectral entropy, robustness, high recognition rate. The threshold adaptive, may be suitable for the case of voice
nnmfcc1
- 不消除静音段,即不通过端点检测,方便说话人识别之后调整语音流的特征显著图.- 37/5000 Bù xiāochú jìngyīn duàn, jí bù tōngguò duāndiǎn jiǎncè, fāngbiàn shuōhuà rén shìbié zhīhòu tiáozhěng yǔyīn liú de tèzhēng xiǎnzhù tú. Does not eliminate the silent section, that is, through the end