搜索资源列表
The_Speex_Codec_Manual_Version_1.2_Beta_3
- Speex是一套开源的专门压缩声音的库，压缩的性能非常高，常用在VoIP或者其它网络程序中。Speex声称自己是不受任何专利限制，并授权根据修订后的BSD许可证发布。它可以用来与Ogg容器格式或直接在UDP / RTP协议下传输。 这份是Speex的编码手册英文版，下面的地址是维基百科中关于Speex的介绍: http://en.wikipedia.org/wiki/Speex-Speex is a free software speech codec that may be used on
Wiener
- 这是一个wiener滤波程序，对语音信号滤波。里面有详细的word文档说明-This is a wiener filtering process to filter the speech signal. There are detailed notes word document
用matlab编的语音增强的程序
- 用matlab编的语音增强的一个程序，是用维纳滤波实现的，-Matlab made use of a speech enhancement procedure, Wiener filter is used to achieve,
HMM100
- HMM matlab 源代码，可用于语音识别，是一种经典的算法，有广泛的应用范围。-HMM matlab source code, can be used for speech recognition is a classical algorithm, a wide range of applications.
noise_estimation
- Noise estimation for speech enhancement
dss
- 声纹识别的特征参数提取,盲信号用于语音识别maltab程序代码,里面有相关语音文件，很不错 -Voiceprint identification of the feature extraction and blind signal for speech recognition maltab code, which has the relevant sound files, very good
noisex
- 递归度信号处理.可用语语音信号处理,如端点检测,清浊音分割.-Recursive-degree signal processing. Can be language speech signal processing, such as endpoint detection, segmentation Voicing.
matlab-speech-frames-using-sub
- 汉明窗，matlab语音分帧使用，function函数，直接在编辑窗口调用-Hamming window, matlab speech frames using sub, function function call directly in the edit window
vad
- 几篇带噪声语音信号端点检测算法的论文，希望对大家有用-Speech signal with noise several endpoint detection algorithm for papers, in the hope that useful
1232sds
- 语音分析的一个工具箱,包括语音合成,语音编码,语音识别方面的一系列小函数,对语音分析很有帮助-A tool of speech analysis, including speech synthesis, speech coding, speech recognition a series of small function useful for speech analysis
Myspeech
- 基于microsoft speech sdk的语音识别代码程序-Microsoft speech sdk-based speech recognition procedures code
lpc
- matlab 求线性倒谱系数,用于语音识别-matlab linear cepstral coefficients for speech recognition
zl
- 基于神经网络的语音识别技术研究 基于神经网络的语音识别技术研究-Neural Network Based Speech Recognition Technology based on neural network speech recognition technology research
spectral_speech_enhancement
- 在强噪声环境下，说话人话音受到很强烈的干扰，语音增强是很有必要的。在TDS5410-TDK实验板，实现了谱衰减算法。主要包括有声/无声检测算法、发送/接收缓冲区的调度、语音降噪算法。试验结果表明，其降噪效果明显，试听效果较好。 -In strong noise environment, the speaker voice by the very strong interference, speech enhancement is necessary. TDS5410-TDK experim
MFCCcanshu
- 6篇有关语音识别特征参数的科技论文，主要包括MFCC参数LPCC参数以及小波应用于特征提取的研究-6 on the speech recognition feature parameters of scientific papers, including MFCC parameters LPCC parameters and wavelet feature extraction applied to the study
DAIMA
- 基于麦克风阵波束形成的谱相减方法在语音增强中的应用-Microphone array beamforming based on the spectral subtraction method speech enhancement application
sapi
- 微软speech api SDK5.1文档-Microsoft speech api SDK5.1 document
svm--km
- 这是一个很好的支持向量机工具箱，它可用于模式识别，图像识别，文字识别，语音识别和手写体识别等领域。-This is a very good support vector machine toolbox, it can be used for pattern recognition, image recognition, text recognition, speech recognition and handwriting recognition and other fields.
htkbook
- 语音识别程序HTK的开发文档，对HTK新手很有帮助！-HTK Speech Recognition program development documentation for novice HTK helpful!
melodyRecognition
- 自动语音识别源码对非特定人的孤立词语音识别算法 进行研究。考虑到语音识别技术在嵌入式系统处理能力较弱、存储空间有限的问 题上进行算法的选择和优化，以提高系统的鲁棒性，减少系统的 -Automatic speech recognition source code for non-specific human isolated word speech recognition algorithm research. Taking into account the voice recogni