搜索资源列表
mfcc2FFT
- 语音识别中,语音信号的MFCC系数回溯到FFT系数过程的源码-MFCC speech recognition in the process of source code back FFT
MFCC-
- 展示了MFCC倒谱参数在语音识别和 声调识别中的作用-Shows the MFCC cepstrum parameters in speech recognition and tone recognition of the role
Tone-Via-LDA
- 通过LAD方法,进行有效的声调识别,汉语是一种有声调的语音,声调识别对汉语言的语音识别的意义很大-By the LAD method, effective tone recognition, Chinese is a kind tone of voice, tone recognition of Chinese language voice recognition is quite significant
TIMIT
- 用于语音识别训练,测试的基础库,这就是大名鼎鼎的Timit库-For speech recognition training and testing based library, which is famous Timit library
robot
- 基于vc的C++编程的语音识别,用于控制机器人的运动,源代码开放-Based on the C++ programming vc voice recognition for controlling the robot, open source
speech-recongition-CHMM
- 高性能语音识别系统的实现!包括系统实现,算法实现等。研究语音识别的好书!-High-performance speech recognition system to achieve! Including system implementation, algorithm, etc. Speech recognition research books!
7c2f6c56ed6d
- 一个HMM的Matlab实现方法,可实现孤立词语音识别-Matlab implementation of a HMM methods, an isolated word speech recognition can be achieved
CPPTTSandSR
- 语音识别 与TTS 的一个小程序
code
- MFC基于PC机的 语音识别程序 MFC控件开发-MFC PC-based speech recognition program developed MFC controls
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
Speakerrecognitionbased-on-MFCC
- 这是一篇工学硕士论文,主要说关于说话人语音识别,,以支持向量机为分类器,分别以MFCC和IM-FCC为特征单独执行分类,将得到结果按某种方式融合,取两者之长,最后做出判决来提高说话人识别系统的性能。-Speaker recognition is a kind of technology that take the use of the information contained in the speech signal to identify who is the speaker or to
Speech-recognition-speech-sdk-5.1
- 语音识别 使用微软语音识别库speech sdk 5.1-Speech recognition speech sdk 5.1
ld3320
- 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
myDTW
- dtw算法,进行语音识别,先读取音频信号,存放到matlab路径中即可。这种算法是语音识别的算法之一,非常有效。-algorithm of DTW
1
- - 我用Java写的qq程序,基于Socket通信,C/S模式 [sphinx2-0.6.tar.gz] - 语音识别系统,美国cmu大学开发的基于hmm模型的语音识别系统 [JSP.rar] - 讲解jsp的开发中的常用技巧 非常使用,其中很多经常遇到 -- I qq program written in Java, based on Socket Communications, C/S mode [sphinx2-0.6.tar.gz]- voice recognit
SR-Windows
- 语音识别与处理的程序,主要基于Windows的speech,需要的拿去参考一下。需要安装SDK5.1.-Speech recognition and processing procedures, the main Windows-based speech, the results were OK. Need to take a look.
r
- 用微软的SAPI,实现快速的语音识别。从而实现智能化。-With Microsoft' s SAPI, fast speech recognition. So intelligent.
speaker
- 语音识别技术,就是输入语音信号,通过程序来实现语音识别-Speech recognition technology is the input speech signal, speech recognition through the program to achieve
recognition
- 粒子滤波与语音识别,实际录制的语音,通过上传,编程来实现识别-Particle filtering and voice recognition, the actual recording of the voice, by uploading, programming to achieve recognition
voxx_code_yunyinshibie-
- voxx_code_使用SAPI和VB编写的语音识别和合成的一个程序-voxx_code_ and written in VB using the SAPI speech recognition and synthesis of a program