资源简介
代码亲测可用,直接调用stoi函数,格式是stoi(x,y,fs),分别是干净语音,带噪语音,采样频率
代码片段和文件信息
function d = stoi(x y fs_signal)
% d = stoi(x y fs_signal) returns the output of the short-time
% objective intelligibility (STOI) measure described in [1 2] where x
% and y denote the clean and processed speech respectively with sample
% rate fs_signal in Hz. The output d is expected to have a monotonic
% relation with the subjective speech-intelligibility where a higher d
% denotes better intelligible speech. See [1 2] for more details.
%
% References:
% [1] C.H.Taal R.C.Hendriks R.Heusdens J.Jensen ‘A Short-Time
% objective Intelligibility Measure for Time-Frequency Weighted Noisy
% Speech‘ ICASSP 2010 Texas Dallas.
%
% [2] C.H.Taal R.C.Hendriks R.Heusdens J.Jensen ‘An Algorithm for
% Intelligibility Prediction of Time-Frequency Weighted Noisy Speech‘
% IEEE Transactions on Audio Speech and Language Processing 2011.
%
%
% Copyright 2009: Delft University of Technology Signal & Information
% Processing Lab. The software is free for non-commercial use. This program
% comes WITHOUT ANY WARRANTY.
%
%
%
% Updates:
% 2011-04-26 Using the more efficient ‘taa_corr‘ instead of ‘corr‘
if length(x)~=length(y)
error(‘x and y should have the same length‘);
end
% initialization
x = x(:); % clean speech column vector
y = y(:); % processed speech column vector
fs = 10000; % sample rate of proposed intelligibility measure
N_frame = 256; % window support
K = 512; % FFT size
J = 15; % Number of 1/3 octave bands
mn = 150; % Center frequency of first 1/3 octave band in Hz.
H = thirdoct(fs K J mn); % Get 1/3 octave band matrix
N = 30; % Number of frames for intermediate intelligibility measure (Length analysis window)
Beta = -15; % lower SDR-bound
dyn_range = 40; % speech dynamic range
% resample signals if other samplerate is used than fs
if fs_signal ~= fs
x = resample(x fs fs_signal);
y = resample(y fs fs_signal);
end
% remove silent frames
[x y] = removeSilentframes(x y dyn_range N_frame N_frame/2);
% apply 1/3 octave band TF-decomposition
x_hat = stdft(x N_frame N_frame/2 K); % apply short-time DFT to clean speech
y_hat = stdft(y N_frame N_frame/2 K); % apply short-time DFT to processed speech
x_hat = x_hat(: 1:(K/2+1)).‘; % take clean single-sided spectrum
y_hat = y_hat(: 1:(K/2+1)).‘; % take processed single-sided spectrum
X = zeros(J size(x_hat 2)); % init memory for clean speech 1/3 octave band TF-representation
Y = zeros(J size(y_
- 上一篇:matlab的pwm函数编写
- 下一篇:水平集图像分割的Matlab程序代码
相关资源
- Pattern Recognition and Machine Learning(高清
- MATLAB 编程 第二版 Stephen J. Chapman 著
- 均值滤波和FFT频谱分析Matlab代码
- 《MATLAB扩展编程》代码
- HDB3码、AMI码的MATLAB实现
- 3点GPS定位MATLAB仿真
- MATLAB数字信号处理85个实用案例精讲入
- matlab从入门到精通pdf94795
- 欧拉放大论文及matlab代码
- 跳一跳辅助_matlab版本
- 全面详解LTE MATLAB建模、仿真与实现
- MIMO-OFDM无线通信技术及MATLAB实现_孙锴
- MATLAB Programming for Engineers 4th - Chapman
- matlab 各种谱分析对比
- 分数阶chen混沌matlab程序
- 基于粒子群算法的非合作博弈的matl
- MATLAB车流仿真 包括跟驰、延误
- matlab空间桁架计算程序
- 基于MATLAB的图像特征点匹配和筛选
- DMA-TVP-FAVAR
- GPS信号的码捕获matlab代码.7z
- 一维光子晶体MATLAB仿真代码吸收率折
- newmark法源程序
- 传统关联成像、计算鬼成像matlab
- pri传统分选算法
- 摆动滚子推杆盘形凸轮设计
- 医学图像重建作业matlab源码
- Matlab实现混沌系统的控制
- 检测疲劳驾驶
- Matlab锁相环仿真-Phase Locked Loop.rar
评论
共有 条评论