paper4

说话人性别识别matlab程序，基音检测、共振峰检测、GMM模型识别(Speaker sex recognition matlab program, pitch detection, formant detection, GMM model identification)

LD3320 是一颗基于非特定人语音识别（SI-ASR：Speaker-Independent Automatic Speech Recognition）技术的语音识别/声控芯片。提供了真正的单 芯片语音识别解决方案。 LD3320 芯片上集成了高精度的A/D 和D/A 接口，不再需要外接辅助的 Flash 和RAM，即可以实现语音识别/声控/人机对话功能。并且，识别的关键词 语列表是可以动态编辑的。(Voice Recognition ；Speech Recognition ；Speech recognition technology )

回声消除算法比较，仿射投影APA与NLMS算法比较(Echo cancellation apa nlms)

attention model for saliency detection.

语音信号分帧后，计算每帧信号的短时平均能量(After the speech signal is framed, the short-term average energy of each frame signal is calculated)

实现语音识别，使用HTK工具。README描述了具体的训练过程。(Voice recognition, using HTK tools. README describes the specific training process.)

（1）理解矢量量化的基本原理。 （2）掌握矢量量化器设计的LBG方法。 （3）运用LBG方法获取语音短时平均能量码书((1) to understand the basic principles of vector quantization. (2) master the vector quantizer design LBG method. (3) Using the LBG method to obtain the speech short time average energy code book)

语音信号处理中用于说话认识别中预处理部分的分帧函数代码(Speech signal processing for speech understanding in other parts of the sub-frame in the pre-function code)

有关语音的matlab源程序,其中包含语音的频谱分析等.(Matlab source code on the voice, including voice spectrum analysis.)

matlab编写的muCVSD语音编码解码器，参数可调，十分方便(matlab prepared muCVSD speech codec parameter adjustable, very convenient)