资源列表
Large-Vocabulary-SR
- The Use of Context in Large Vocabulary Speech Recognition.Julian James Ode-The Use of Context in Large Vocabulary Speech Recognition.Julian James Odell
hdda_toolbox_1.1
- The High Dimensional Discriminant Analysis (HDDA) toolbox contains an efficient supervised classifier for high-dimensional data. This classifier is based on Gaussian models adapted for high-dimensional data. Reference: C. Bouveyron, S. Girard
ISpeech-recogs
- 基于HMM的孤立词语音识别别程序，非常有用。可直接使用。 -Isolated word HMM-based speech recognition procedures, very useful. Complete source code can be used directly.
mfcc2
- mfcc 语音识别的很好用的一个工具，可以帮助快速提取特征参数~-mfcc good use of voice recognition as a tool to help quickly extract feature parameters ~
Labview-luyinxitong
- 基于Labview的双声道语音录制系统，内涵报告，解释制作步骤。-Labview-based two-channel audio recording system, meaning the report, explained production steps.
AutoDial
- C# WinForm下实现API自动拨号功能,支持多个网络-C# WinForm API autodial feature, and support for multiple network
LCS-VC60
- C语言DTW算法实现,主要功能: 1)快速近邻DTW比较 2)算法稳定 3)节省内存-== Key features == 1) Fast Dynamic Time Warping nearest neighbor cost retrieval. 2) Persistence 3) External-memory: you need only a constant amount of RAM
gaibiancaiyanglv
- 语音文件可进行采样率的修改，只要更改程序中的参数即可-Sampling rate of audio files can be modified, as long as you can change the parameters of the program
voice
- 对一段语音进行变速变调等多种处理的MATLAB样例程序。-Variable-speed modulation of a variety of voice processing sample MATLAB program.
STRAIGHTV40pcode
- 最好的语音合成代码，出自日本，是以源-滤波器模型合成语音质量最好的开源代码，注意，此MATLAB代码，只有P-CODE 如要源码，需向作者申请-The best speech synthesis code, from Japan, is source- filter model synthesizer voice quality the best open source code, note that this MATLAB code, only the P-CODE to source req
HTK-3[1].4.1
- 最新语音识别HTK工具包，不需要帐号就可以下载-newest Speech recognition kit
acm
- acm语音格式转换 a率、pcm等互转、多年前写的-acm audio format conversion a rate, pcm, etc. conversion, written many years ago