资源列表
MFCC-by-CPP
- MFCC 提取算法 C++实现 挺好的可以实现-The MFCC extract algorithm C++ achieve
aaa
- 基于windows speech的语音识别-Based on windows SPeech speech recognition
Distributed-speech-processing
- 分布式语音识别（DSR）是为了减轻语音处理前端的运算压力而产生的一种系统化的语音处理流程，目前欧洲电信标准化协会（ETSI）已经发布了多个版本的DSR标准C代码。本代码利用C67系列DSP芯片的特性，对ETSI标准DSR代码进行了优化。可以在ccs studio平台下编译运行。-Distributed Speech Recognition is a systemized speech processing architecture, that is used to unburden the fr
Sound-intensity-frequency-detection
- 声强频率检测程序，用于分离MP3音乐中不同频率的声段-Sound intensity frequency detection procedures for the different frequencies of the sound segments in the separator MP3 music
speech-signal
- 本资料中的程序可以提取语音信号的短时能量、过零率、短时谱、语谱图和线性预测系数。-The information in the program can extract short-time energy of the speech signal, the zero crossing rate, short-time spectrum, spectrogram and linear prediction coefficients.
speech-synthesis
- 关于语音合成的matlab程序，其中包括声音变调，加速和减速-Matlab program for speech synthesis, including sound transposition, acceleration and deceleration
normal
- 语音频谱整个处理流程,包括分帧，端点检测之类的东西-The whole processing flow of the speech spectrum
01188289
- this the IEEE paper for speech compression-this is the IEEE paper for speech compression
point_detect
- 该MATLAB程序实现语音端点检测,能够检测出一个音频文件中的话音部分-This MATLAB program realizes the voice activity detection
klatt_for_2011
- klatt并级联共振峰语音合成器，通过输入语音的特征参数（包括基音频率、共振峰参数等）来合成语音。-the Klatt Cascade-Parallel Formant Speech Synthesizer，synthesizing voice via inputting the characteristic parameters of the speech （including the pitch frequency, formant parameters, etc.)
DTWvoice-recognition
- DTW语音识别算法,MATLAB对DTW算法编程，实现对语音的识别-voice recognition
59159000-Speaker-Recognition-Using-MATLAB
- speaker detection using different function