资源列表
Web_Fide_Doc_System
- 公文查询系统源码 公文查询系统源码 公文查询系统源码 -公文查询系统源码
windowfilter
- 功能一句话：Design Linear-Phase FIR using Window: rectangular window,Hamming window,Bartlett window。是学习信号处理FIR滤波器设计时很好的代码。-Design Linear-Phase FIR using Window: rectangular window,Hamming window,Bartlett window
fenzhenspeechenhance
- 一个用谱减法实现的语音消燥程序，该程序在本网站下载通过修改可直接运行，效果良好，便于初学者入门。-The realization of a spectral subtraction with extinction dry voice program to download on this site can be directly run by modifying the results were very good, easy entry for beginners.
HTS-2.1_for_HTK-3.4
- HTS version 2.1 includes hidden semi-Markov model (HSMM) training/adaptation/synthesis, speech parameter generation algorithm considering global variance (GV), SMAPLR/CSMAPLR adaptation, and other minor new features.
G723
- G.723 是H.323协议族中的音频编码标准之一，也是应用非常广泛的音频标准，该压缩文件包含了ITU G.723的标准，同时也包含了对应的源代码，可用VC++进行编译。-G.723 is the H.323 protocol suite in one of the audio coding standard, but also the application of a very wide range of audio standards, the compressed file contai
gongxiang
- 此程序包括非均匀采样 PCM编解码、语音STFT等-The program includes non-equal sampling ,PCM coding and decoding,STFT of audio signal
voice1
- 這是一個凌陽單晶片 開發的語音辨識程式 使用sm480自動撥放 以及bsr語音訓練函數-Sunplus is a single-chip speech recognition program developed by sm480 automatically play as well as the use of voice training function bsr
fmntest1
- this file is in matlab.discribe the formant function in matlab
CG-GMM
- Voice Conversion based on Joint Pitch and Spectral Transformation with Component Group-GMM.pdf
audio processing
- 语音信号处理-对输入语音信号进行端点检测和基音轨迹的检测（利用acf、amdf和acf/amdf三种方法）。-Speech Signal Processing- the input voice signal trajectory endpoint detection and pitch detection (using acf, amdf and acf/amdf three methods).
yysbjdwb
- 这是用易语言语音识别例程和机读文本例程，压缩包中的 ‘yysb’为语音识别例程，‘jdwb’为机读文本例程，希望这些例程能对新手有帮助！-It is easy to use language speech recognition and machine-readable text routines routines, compressed package ' yysb' routines for speech recognition, ' jdwb' routines
part2
- The codes in the zipped folder is used for digit recognition. GMM is used to model the speakers.