【语音识别】基于matlab GUI HMM 0~9数字语音识别【含Matlab源码 1393期】

988 阅读6分钟

一、隐马尔可夫模型简介

隐马尔可夫模型(Hidden Markov model, HMM)是一种结构最简单的动态贝叶斯网的生成模型,它也是一种著名的有向图模型。它是典型的自然语言中处理标注问题的统计机器学模型,本文将重点介绍这种经典的机器学习模型。 1 引言 假设有三个不同的骰子(6面、4面、8面),每次先从三个骰子里面选择一个,每个骰子选中的概率为1/3,如下图所示,重复上述过程,得到一串数值[1,6,3,5,2,7]。这些可观测变量组成可观测状态链。同时,在隐马尔可夫模型中还有一条由隐变量组成的隐含状态链,在本例中即骰子的序列。比如得到这串数字骰子的序列可能为[D6, D8, D8, D6, D4, D8]。 在这里插入图片描述 隐马尔可夫型示意图如下所示: 在这里插入图片描述 图中,箭头表示变量之间的依赖关系。图中各箭头的说明如下: 在这里插入图片描述 在任意时刻,观测变量(骰子)仅依赖于状态变量(哪类骰子),同时t时刻的状态qt仅依赖于t-1时刻的状态qt-1。这就是马尔科夫链,即系统的下一时刻仅由当前状态(无记忆),即“齐次马尔可夫性假设”

2 隐马尔可夫模型的定义 根据上面的例子,这里给出隐马尔可夫的定义。隐马尔科夫模型是关于时序的概率模型,描述由一个隐藏的马尔可夫链随机生成不可观测的状态随机序列,再由各个状态生成一个可观测的随机序列的过程,隐藏的马尔可夫链随机生成的状态序列,称为状态序列(也就上面例子中的D6,D8等);每个状态生成一个观测,而由此产生的观测随机序列,称为观测序列(也就上面例子中的1,6等)。序列的每个位置又可以看作是一个时刻。 隐马尔可夫模型由初始的概率分布、状态转移概率分布以及观测概率分布确定。具体的形式如下,这里设Q是所有可能的状态的集合,V是所有可能的观测的集合,即有: 在这里插入图片描述 在这里插入图片描述 在这里插入图片描述 3 前向算法
在这里插入图片描述 在这里插入图片描述 对于步骤一的初始,是初始时刻的状态i1 = q1和观测o1的联合概率。步骤(2) 是前向概率的递推公式,计算到时刻t+1部分观测序列为o1,o2,...,ot,ot+1 且在时刻t+1处于状态qi的前向概率。如上图所示,既然at(j)是得到时刻t观测到o1,o2,...,ot并在时刻t处于状态的qj前向概率,那么at(j)aji就是到时刻t观测到o1,o2,...,ot并在是时刻t处于qj状态而在时刻t+1到达qi状态的联合概率。对于这个乘积在时刻t的所有可能的N个状态求和,其结果就是到时刻t观测为o1,o2,...,ot,并在时刻t+1处于状态qi的联合概率。最后第三步,计算出P(O|lamda)的结果。

当然这里只是介绍了诸多算法中的一种,类似的还有后向算法(大家可以看相关的书籍进行了解)。对于动态规划的解决隐马尔科夫模型预测问题,应用最多的是维特比算法。

二、部分源代码

function varargout = HMM_VoiceRecognation(varargin)
% HMM_VOICERECOGNATION MATLAB code for HMM_VoiceRecognation.fig
%      HMM_VOICERECOGNATION, by itself, creates a new HMM_VOICERECOGNATION or raises the existing
%      singleton*.
%
%      H = HMM_VOICERECOGNATION returns the handle to a new HMM_VOICERECOGNATION or the handle to
%      the existing singleton*.
%
%      HMM_VOICERECOGNATION('CALLBACK',hObject,eventData,handles,...) calls the local
%      function named CALLBACK in HMM_VOICERECOGNATION.M with the given input arguments.
%
%      HMM_VOICERECOGNATION('Property','Value',...) creates a new HMM_VOICERECOGNATION or raises the
%      existing singleton*.  Starting from the left, property value pairs are
%      applied to the GUI before HMM_VoiceRecognation_OpeningFcn gets called.  An
%      unrecognized property name or invalid value makes property application
%      stop.  All inputs are passed to HMM_VoiceRecognation_OpeningFcn via varargin.
%
%      *See GUI Options on GUIDE's Tools menu.  Choose "GUI allows only one
%      instance to run (singleton)".
%
% See also: GUIDE, GUIDATA, GUIHANDLES

% Edit the above text to modify the response to help HMM_VoiceRecognation

% Last Modified by GUIDE v2.5 12-Oct-2021 20:30:18

% Begin initialization code - DO NOT EDIT
gui_Singleton = 1;
gui_State = struct('gui_Name',       mfilename, ...
                   'gui_Singleton',  gui_Singleton, ...
                   'gui_OpeningFcn', @HMM_VoiceRecognation_OpeningFcn, ...
                   'gui_OutputFcn',  @HMM_VoiceRecognation_OutputFcn, ...
                   'gui_LayoutFcn',  [] , ...
                   'gui_Callback',   []);
if nargin && ischar(varargin{1})
    gui_State.gui_Callback = str2func(varargin{1});
end

if nargout
    [varargout{1:nargout}] = gui_mainfcn(gui_State, varargin{:});
else
    gui_mainfcn(gui_State, varargin{:});
end
% End initialization code - DO NOT EDIT


% --- Executes just before HMM_VoiceRecognation is made visible.
function HMM_VoiceRecognation_OpeningFcn(hObject, eventdata, handles, varargin)
% This function has no output args, see OutputFcn.
% hObject    handle to figure
% eventdata  reserved - to be defined in a future version of MATLAB
% handles    structure with handles and user data (see GUIDATA)
% varargin   command line arguments to HMM_VoiceRecognation (see VARARGIN)

% Choose default command line output for HMM_VoiceRecognation
handles.output = hObject;

% Update handles structure
guidata(hObject, handles);

% UIWAIT makes HMM_VoiceRecognation wait for user response (see UIRESUME)
% uiwait(handles.figure1);


% --- Outputs from this function are returned to the command line.
function varargout = HMM_VoiceRecognation_OutputFcn(hObject, eventdata, handles) 
% varargout  cell array for returning output args (see VARARGOUT);
% hObject    handle to figure
% eventdata  reserved - to be defined in a future version of MATLAB
% handles    structure with handles and user data (see GUIDATA)

% Get default command line output from handles structure
varargout{1} = handles.output;


% --- Executes on button press in button_choose.
function button_choose_Callback(hObject, eventdata, handles)
% hObject    handle to button_choose (see GCBO)
% eventdata  reserved - to be defined in a future version of MATLAB
% handles    structure with handles and user data (see GUIDATA)
% fname: 返回文件名
% panme: 返回文件路径名
% index: 选择的文件类型
global fname
global pname
[fname, pname, index] = uigetfile( { '*.wav', '选择语音文件'} ) ;
set( handles.button_reco, 'Enable', 'on' ) 


% --- Executes on button press in button_reco.
function button_reco_Callback(hObject, eventdata, handles)
% hObject    handle to button_reco (see GCBO)
% eventdata  reserved - to be defined in a future version of MATLAB
% handles    structure with handles and user data (see GUIDATA)
global fname
global pname
global str
    
filename = strcat( pname, '\\', fname ) ;
load('hmm.mat')
% 发音
[ y, fs ] = audioread(filename) ;
sound(y, fs) ;
% 识别
x = wavread(filename);
[x1 x2] = vad(x);
m = mfcc(x);
m = m(x1-2:x2-2,:);
for j=1:10
	pout(j) = viterbi(hmm{j}, m);
end
[d,result_index] = max(pout);
%在static text里显示结果
if result_index == 10



% --- Executes on button press in button_exit.
function button_exit_Callback(hObject, eventdata, handles)
% hObject    handle to button_exit (see GCBO)
% eventdata  reserved - to be defined in a future version of MATLAB
% handles    structure with handles and user data (see GUIDATA)
clear all
close

% --- Executes on selection change in listbox1.
function listbox1_Callback(hObject, eventdata, handles)
% hObject    handle to listbox1 (see GCBO)
% eventdata  reserved - to be defined in a future version of MATLAB
% handles    structure with handles and user data (see GUIDATA)

% Hints: contents = cellstr(get(hObject,'String')) returns listbox1 contents as cell array
%        contents{get(hObject,'Value')} returns selected item from listbox1


% --- Executes during object creation, after setting all properties.
function listbox1_CreateFcn(hObject, eventdata, handles)
% hObject    handle to listbox1 (see GCBO)
% eventdata  reserved - to be defined in a future version of MATLAB
% handles    empty - handles not created until after all CreateFcns called




function edit1_Callback(hObject, eventdata, handles)
% hObject    handle to edit1 (see GCBO)
% eventdata  reserved - to be defined in a future version of MATLAB
% handles    structure with handles and user data (see GUIDATA)

% Hints: get(hObject,'String') returns contents of edit1 as text
%        str2double(get(hObject,'String')) returns contents of edit1 as a double


% --- Executes during object creation, after setting all properties.
function edit1_CreateFcn(hObject, eventdata, handles)
% hObject    handle to edit1 (see GCBO)
% eventdata  reserved - to be defined in a future version of MATLAB
% handles    empty - handles not created until after all CreateFcns called

% Hint: edit controls usually have a white background on Windows.
%       See ISPC and COMPUTER.
if ispc && isequal(get(hObject,'BackgroundColor'), get(0,'defaultUicontrolBackgroundColor'))
    set(hObject,'BackgroundColor','white');
end


% --- Executes on button press in button_clear.
function button_clear_Callback(hObject, eventdata, handles)
% hObject    handle to button_clear (see GCBO)
% eventdata  reserved - to be defined in a future version of MATLAB
% handles    structure with handles and user data (see GUIDATA)
function f=enframe(x,win,inc) 
%ENFRAME split signal up into (overlapping) frames: one per row. F=(X,WIN,INC) 
% 
%	F = ENFRAME(X,LEN) splits the vector X up into 
%	frames. Each frame is of length LEN and occupies 
%	one row of the output matrix. The last few frames of X 
%	will be ignored if its length is not divisible by LEN. 
%	It is an error if X is shorter than LEN. 
% 
%	F = ENFRAME(X,LEN,INC) has frames beginning at increments of INC 
%	The centre of frame I is X((I-1)*INC+(LEN+1)/2) for I=1,2,... 
%	The number of frames is fix((length(X)-LEN+INC)/INC) 
% 
%	F = ENFRAME(X,WINDOW) or ENFRAME(X,WINDOW,INC) multiplies 
%	each frame by WINDOW(:) 
 
%	
% 

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% 

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% 
 
nx=length(x); 
nwin=length(win); 
if (nwin == 1) 
   len = win; 
else 
   len = nwin; 
end 
if (nargin < 3) 
   inc = len; 
end 
nf = fix((nx-len+inc)/inc); 
f=zeros(nf,len); 
indf= inc*(0:(nf-1)).'; 
inds = (1:len); 
f(:) = x(indf(:,ones(1,len))+inds(ones(nf,1),:)); 
if (nwin > 1) 
    w = win(:)'; 
    f = f .* w(ones(nf,1),:); 
end 
 


三、运行结果

在这里插入图片描述

四、matlab版本及参考文献

1 matlab版本 2014a

2 参考文献 [1]韩纪庆,张磊,郑铁然.语音信号处理(第3版)[M].清华大学出版社,2019. [2]柳若边.深度学习:语音识别技术实践[M].清华大学出版社,2019.