搜索资源列表
FormantTracker(matlab)
- 检测语音信号的共振峰 ％ gender = gender_detector(X,Fs) ％ ％ This function will use a pitch detection algorithm to decide if the speaker is MALE(0) or FEMALE (1). ％ It is designed to work with short speech samples (up to or greater than 50 ms). The funct
vad(x)
- 是关于双门限端点检测算法的Matlab程序，通过编译了，粘贴到WORD里了-is on the threshold double Endpoint Detection Algorithm Matlab program, compile and paste into a Word Lane
67506267enframe
- ENFRAME split signal up into (overlapping) frames: one per row. F=(X,WIN,INC)
fastica
- FASTICA - Fast Independent Component Analysis ％ ％ FastICA for Matlab 7.x and 6.x ％ Version 2.5, October 19 2005 ％ Copyright (c) Hugo G鋠ert, Jarmo Hurri, Jaakko S鋜el� and Aapo Hyv鋜inen. ％ ％ FASTICA(mixedsig) estimates the independent
MFCC 对输入的语音序列x进行MFCC参数的提取
- 对输入的语音序列x进行MFCC参数的提取，返回MFCC参数和一阶差分MFCC参数，Mel滤波器的阶数为24,fft变换的长度为256，采样频率为8000Hz，对x 256点分为一帧. -The voice of the input MFCC parameters on the sequence of x, return to MFCC parameters and extracted a order difference MFCC parameters, Mel filter for th
vc_speak_recegnition
- vc++语音识别 vc++语音识别 vc++语音识别 -VC++speak_recognition
fxlms
- ％％ Active Noise Control Using a Filtered-X LMS FIR Adaptive Filter ％ This demonstration illustrates the application of adaptive filters to the ％ attenuation of acoustic noise via active noise control. - Active Noise Control Using a Filtered-X L
pitchwatch
- function pitchwatch(x,Ts) Plot the pitch keys. pitchwatch(x,[Ts]) :: Syntax The array x is the input signal and Ts is the (optional) sampling period. Example on use: [x,Fs] = wavread( Hum.wav ) pitchwatch(x,1/Fs) :: Inf
adaptdemos
- Active Noise Control Using a Filtered-X LMS FIR Adaptive Filter.
massey_speech_project
- This the source code to the Massey School of Engineering Speech project.It has the Alice Artificial Intelligence engine included and only needs a Microsoft Agent character to work. The program will work without MSagent as well however. The program
mic1
- There are four major types of adaptive filtering configurations adaptive system identification, adaptive noise cancellation, adaptive linear prediction, and adaptive inverse system. All of the above systems are similar in the implementation of the al
Speech-recognition
- 运行结果表明该说话人识别系统的识别能力是比较理想的，识别率为88 ，语音库3识别不成功的原因主要有两个，一方面3的录音本身噪音相对大些，导致系统很难识别，另一方面，识别系统的算法还不是很理想，导致识别准确率不是100 。- DISTEU Pairwise Euclidean distances between columns of two matrices Input: x, y: Two matrices whose each column
LPMCC-Speach-Emotion-Recognition
- 基于LPMCC的语音识别系统实现 语音识别可实现人机交互和语音控制，在X-业控制、消费电子等领域都有广泛应用。结合人发音的生理 结构的特点，使用LPMCC(LPC倒谱美尔变换)作为特征向量，采用动态规划算法作为核心识别算法，在TMS320VC5402芯片上实现了特定人、孤立词的高性能实时识别系统。-Speech Recognition System Based On LPMCC Speech recognition can achieve human—computer intera
4.8k_CELP
- 语音CELP压缩解压源代码（C语音)- Pronunciation CELP compression decompression source code (C pronunciation) - * 4800 bps CELP Characteristics * * Spectrum Pitch Code Book * ------------- ---------------
sphinx3-0.4.1
- sphinx系统是一个拥有悠久历史的语音识别系统，李开复自称第一个sphinx是他写的。 传说 中是第一个实用的10数字语音系统。 是由卡奈基.美隆大学研发。 sphinx3.x是基于C语言的最新版本,sphinx和 sphinx2请大家不要去研究了。 sphinx for ppc是一个在PocketPc上实现的嵌入式语音识别系统。 而 sphinx4是完全用JAVA编写实现的语音识别系统， 因为JAVA的特性，在平台间移植
anglecos
- 利用夹角余弦距离进行样本数据分类。实现步骤主要分为以下两部分：a、待测样品X与训练集里每个样品Xi的距离采用夹角余弦距离公式计算。b、循环计算待测样品和训练集中各已知样品之间的距离，找出距离待测样品最近的已知样品，该已知样品的类别就是待测样品的类别。-Using the sample data classification Angle cosine distance.Implementation steps are divided into the following two parts: a,
ampp
- 用于提取语音信号的能量谱的函数,ampp(s,a,b,c)，x为输入信号，a,b,c用于指定subplot函数的作图位置-A function for extracting the energy spectrum of the speech signal, ampp (s, a, b, c), x is the input signal, a, b, c is used to specify the location of subplot mapping function
zcrr
- 用于计算语音信号过零率的函数zcrr，zcrr（x，a，b，i），x为输入，a，b，c为指定subplot函数的参数-Function zcrr for calculating zero-crossing rate of the speech signal, zcrr (x, a, b, i), x is the input, a, b, c as a function of the parameter specifies subplot
mfcc
- 本段程序实在MATLAB环境下对输入的语音序列x进行MFCC参数的提取，返回MFCC参数和一阶差分MFCC参数。-Voice input sequence x extracted MFCC parameters, return parameters and the first-order difference MFCC MFCC parameters