资源简介
本项目建立了一个小的语音库(8男8女),编写mfcc函数提取出语音的mfcc特征,然后利用svm进行训练和测试,实现性别识别,并创建gui进行功能展示,正确率为93.75%。本代码功能尚比较简单,有待继续完善。
代码片段和文件信息
function [ CC FBE frames ] = mfcc( speech fs Tw Ts alpha window R M N L )
% MFCC Mel frequency cepstral coefficient feature extraction.
%
% MFCC(SFSTWTSALPHAWINDOWRMNL) returns mel frequency
% cepstral coefficients (MFCCs) computed from speech signal given
% in vector S and sampled at FS (Hz). The speech signal is first
% preemphasised using a first order FIR filter with preemphasis
% coefficient ALPHA. The preemphasised speech signal is subjected
% to the short-time Fourier transform analysis with frame durations
% of TW (ms) frame shifts of TS (ms) and analysis window function
% given as a function handle in WINDOW. This is followed by magnitude
% spectrum computation followed by filterbank design with M triangular
% filters uniformly spaced on the mel scale between lower and upper
% frequency limits given in R (Hz). The filterbank is applied to
% the magnitude spectrum values to produce filterbank energies (FBEs)
% (M per frame). Log-compressed FBEs are then decorrelated using the
% discrete cosine transform to produce cepstral coefficients. Final
% step applies sinusoidal lifter to produce liftered MFCCs that
% closely match those produced by HTK [1].
%
% [CCFBEframeS]=MFCC(...) also returns FBEs and windowed frames
% with feature vectors and frames as columns.
%
% This framework is based on Dan Ellis‘ rastamat routines [2]. The
% emphasis is placed on closely matching MFCCs produced by HTK [1]
% (refer to p.337 of [1] for HTK‘s defaults) with simplicity and
% compactness as main considerations but at a cost of reduced
% flexibility. This routine is meant to be easy to extend and as
% a starting point for work with cepstral coefficients in MATLAB.
% The triangular filterbank equations are given in [3].
%
% Inputs
% S is the input speech signal (as vector)
%
% FS is the sampling frequency (Hz)
%
% TW is the analysis frame duration (ms)
%
% TS is the analysis frame shift (ms)
%
% ALPHA is the preemphasis coefficient
%
% WINDOW is a analysis window function handle
%
% R is the frequency range (Hz) for filterbank analysis
%
% M is the number of filterbank channels
%
% N is the number of cepstral coefficients
% (including the 0th coefficient)
%
% L is the liftering parameter
%
% Outputs
% CC is a matrix of mel frequency cepstral coefficients
% (MFCCs) with feature vectors as columns
%
% FBE is a matrix of filterbank energies
% with feature vectors as columns
%
% frameS is a matrix of windowed frames
% (one frame per column)
%
% Example
% Tw = 25; % analysis frame duration (ms)
% Ts = 10; % analysis frame shift (ms)
% alpha = 0.97; % preemphasis coefficient
% R = [ 300 3700 ]; % frequency range to
属性 大小 日期 时间 名称
----------- --------- ---------- ----- ----
目录 0 2018-04-27 21:41 MFCC_2\
文件 7190 2018-04-21 21:05 MFCC_2\mfcc.m
文件 4797 2018-04-21 21:19 MFCC_2\trifbank.m
文件 10707 2018-04-23 16:30 MFCC_2\unti
文件 9006 2018-04-23 16:30 MFCC_2\unti
目录 0 2018-04-27 21:41 MFCC_2\Validation_test_set\
文件 914076 2018-04-21 22:19 MFCC_2\Validation_test_set\f1.wav
文件 983706 2018-04-21 22:23 MFCC_2\Validation_test_set\f2.wav
文件 998454 2018-04-21 22:25 MFCC_2\Validation_test_set\f3.wav
文件 919192 2018-04-21 22:27 MFCC_2\Validation_test_set\f4.wav
文件 1036958 2018-04-21 22:29 MFCC_2\Validation_test_set\f5.wav
文件 1190964 2018-04-21 22:31 MFCC_2\Validation_test_set\f6.wav
文件 1052724 2018-04-21 22:34 MFCC_2\Validation_test_set\f7.wav
文件 980224 2018-04-21 22:36 MFCC_2\Validation_test_set\f8.wav
文件 887246 2018-04-21 22:21 MFCC_2\Validation_test_set\m1.wav
文件 790168 2018-04-21 22:24 MFCC_2\Validation_test_set\m2.wav
文件 1046376 2018-04-21 22:26 MFCC_2\Validation_test_set\m3.wav
文件 929228 2018-04-21 22:28 MFCC_2\Validation_test_set\m4.wav
文件 1033064 2018-04-21 22:30 MFCC_2\Validation_test_set\m5.wav
文件 1061118 2018-04-21 22:33 MFCC_2\Validation_test_set\m6.wav
文件 952576 2018-04-21 22:35 MFCC_2\Validation_test_set\m7.wav
文件 907726 2018-04-21 22:36 MFCC_2\Validation_test_set\m8.wav
文件 6993 2018-04-21 21:19 MFCC_2\vec2fr
相关资源
- 代码mfcc的pro
- SVM C语言实现
- Frogs_MFCCs.csv
- 用遗传算法实现语音识别--基于mfcc参
- 基于MFCC的GMM的说话人识别.rar
- 文本有关的说话人识别系统
- 语音识别GMM模型
- matlab算法实现声纹识别,带界面
- C++实现支持向量SVM机分类器.zip
- 人脸性别识别
- 基于PCA和SVM的人脸识别系统
- opencv SVM图像分类工程文件
- 中英语种识别matlab程序包含40个测试音
- 基于SVM与人工神经网络的车牌识别O
- 基于SVM与人工神经网络的车牌识别C
- 基于mfcc特征的dtw算法实现
- 训练SVM分类器
- svm分类算法(附实验报告)
- HOG+SVM代码及文档说明
- 基于SVM的语音情感识别系统
- mfcc特征提取,c++代码实现
- c++代码LSSVM支持向量机
- 基于vc++的SVM
- 语音信号分析与处理及其MATLAB实现L
- svm训练图像
- MATLAB2014a与vs2012混合编译解决使用li
- 语音信号MFCC特征提取
- SVM+OPENCV+交叉验证 计算识别率
- 基于MFCC和SVM的说话人性别识别
- 行人检测 opencv
评论
共有 条评论