搜索资源列表
G711andVAD
- g711、VAD的激活算法，公司内重要价值的dsp压缩代码。
G711
- G711压缩解压、VAD语音激活算法，非常有用，效率很高
DSP公司内部使用的
- 公司内重要价值的dsp压缩代码，强烈推荐！！！含（G711压缩解压，VAD算法语音激活算法）-company value of the DSP code compression and strongly recommended! ! ! Containing (G711 codecs, voice-activated VAD algorithm algorithm)
VAD_Eval
- EasyVAD is an implementation of VAD（Voice Active Detection）. EasyVAD support multiple channels concurrent. There is no limit on concurrent channels and it can up to thousands channels-EasyVAD is an implementation of VAD（Voice Active Detection）.
vad
- 语音滤波短时能量 短时过滤率 端点检测 都能得到相应的仿真波形-Speech s filtering the short time percolation of a short time energy a rate to carry to order examinations can get to homologously imitate true wave a form
G711CodecVAD
- 在dsp中使用G711压缩解压，以及VAD算法和语音激活算法，非常不错的源代码与算法参考例子-The use of G711 in the dsp compression decompression, as well as the VAD algorithm and voice activation algorithm, a very good reference source code examples and algorithms
VAD_algorithm_and_FPGA_design
- 论文，关于VAD检测与FPGA如何实现的，基于短时能量-based on short energy ,VAD detected algorithm and FPGA design
TIchinese_A1092
- G729B源码1.4版本，含CS-AELP,DTX,VAD,CNG。已验证，调试。-G729B source code 1.4 version, with CS-AELP, DTX, VAD, CNG. Verified, debugging.
EasyVAD
- EasyVAD is an implementation of VAD（Voice Active Detection）. EasyVAD support multiple channels concurrent. There is no limit on concurrent channels and it can up to thousands channels-EasyVAD is an implementation of VAD（Voice Active Detection）.
Vocalinx
- To evaluate a VAD, its output using test recordings is compared with those of an "ideal" VAD - created by hand-annotating the presence/absence of voice in the recordings. The performance of a VAD is commonly evaluated on the basis of the following fo
ssubmmsev
- performs speech enhancement using the MMSE or log MMSE criteria with VAD-based noise estimate
Voice Discern For STM32F
- 于市售 STM32 开发板上实现特定人语音识别处理项目。识别流程是：预滤波、ADC、分帧、端点检测、预加重、加窗、特征提取、特征匹配。端点检测(VAD)采用短时幅度和短时过零率相结合。检测出有效语音后，根据人耳听觉感知特性,计算每帧语音的 Mel 频率倒谱系数(MFCC)。然后采用动态时间弯折(DTW)算法与特征模板相匹配,最终输出识别结果。先用Matlab对上述算法进行仿真，经数次试验求得算法内所需各系数的最优值。而后将算法移植到 STM32 开发板上，移植过程中根据 STM32 上存储空间相
STM32-Speech-Recognition-Master
- 于市售 STM32 开发板上实现特定人语音识别处理项目。识别流程是：预滤波、ADC、分帧、端点检测、预加重、加窗、特征提取、特征匹配。端点检测(VAD)采用短时幅度和短时过零率相结合。检测出有效语音后，根据人耳听觉感知特性,计算每帧语音的 Mel 频率倒谱系数(MFCC)。然后采用动态时间弯折(DTW)算法与特征模板相匹配,最终输出识别结果。先用Matlab对上述算法进行仿真，经数次试验求得算法内所需各系数的最优值。而后将算法移植到 STM32 开发板上，移植过程中根据 STM32 上存储空间相