资源列表
10.1.1.158.3297
- book, speech recognition
The-research-of-anti-niose-speech
- 论文首先介绍了传统的语音特征参数MFCC,它是基于人耳听觉 特性设计的一种特征参数,在静音环境下能得到较高的识别率,但在 信噪比较低时识别率急剧下降,不利于实用化。本文通过对MFCC算 法的分析和研究,发现其中的FFT和DCT在整个时频空间使用固定的 。分析窗,这不符合语音信号特性,而小波变换具有多分辨率特性,更 符合人耳的听觉特性。因此,本文将小波变换和MFCC算法相结合, 提出了三种新的语音识别特-Speech recognition has wide use in
RecordHWnd
- 基于vC6.0开发的录音机,可实现音乐的录制,暂停,回放功能。-Developed based on vC6.0 recorder, enabling music recording, pause playback.
aaSAeRealplay
- 自己编写的语音播放程序,适合初学者,欢迎下载-Voice player to write your own, suitable for beginners, are welcome to download
副本
- 在开源的MIDI转乐谱代码上添加录音功能(Adding audio recording on the open source MIDI code)
HTK-Linux-3.3.tar
- 语音识别源代码,是剑桥大学机器人视觉组开发的。识别效果比较好。-HTK is a toolkit for use in research into automatic speech recognition
feature_extraction_in_speech_recognition2004
- 语音识别中的特征提取的IEEE的期刊论文2004年
speakercode1
- Speaker Identification using MFCC feature and VQ training, very clear MATLAB code
Edinburgh
- 英国爱丁堡大学的语音处理系统,可以找到大部分语音处理/识别/合成所需要的算法-University of Edinburgh voice processing system that can find most of voice processing / recognition / synthesis algorithms needed
SkypeAPI
- skypeapplication 这个工程文件包含SkypeAPIApplication.h SkypeAPIApplication.cpp SkypeAPIApplication.rc SkypeAPIApplication.clw res\SkypeAPIApplication.ico res\SkypeAPIApplication.rc2-This file contains a summary of what you will find in each of the
STM32F10x_DSP_Lib_V1.0.1
- stm dsp的源文件 和例程 ,做一些简单的dsp开发和学习-stm dsp source files and routines, do some simple dsp development and learning
computer-for-lipreading
- 在自动语音识别系统中研究唇语识别,有助于提高识别的正确率-In automatic speech recognition system in recognition of lips, helps to improve recognition accuracy