-

Discrete_Time_Speech_SP_Quatieri/README.txt

@@ -0,0 +1,60 @@
+
+	SUPPLEMENTARY MATLAB MATERIAL FOR
+	---------------------------------
+
+	DISCRETE-TIME SPEECH SIGNAL PROCESSING: Principles and Practice
+	---------------------------------------------------------------
+
+	by Thomas F. Quatieri
+	---------------------
+
+	Located in this Prentice Hall web site compartment are functions, scripts, workspaces, 
+	and data required by the MATLAB exercises in the text: Discrete-Time Speech Sign
+	specific cases of a certain class of speech signal, i.e., the waveforms often can 
+	be replaced by other examples with similar characteristics that serve the instructive 
+	purpose of the exercise.
+
+	Each chapter has its own directory structure. As an example, the directory 
+	for Chapter 13 consists of:
+
+	chapter13/
+	---------
+
+	Backup and Data Directories:
+	---------------------------
+	Back/
+	Data/
+
+	Workspaces:
+	----------
+	ex11M1.mat          
+	ex11M2.mat          
+
+	Functions and Scripts:
+	---------------------
+	amfm_sep.m          
+	gaussian_filt.m     
+	wigner.m
+	specgram_speech.m
+	cross.m             
+	stftm.m
+
+	In addition, occasionally, readme files appear within the sub-directories. 
+	These readme files are in text format and describe or clarify contents of 
+	the sub-directory or a particular MATLAB exercise.
+
+	Speech files in the Data directory are in both pcm and wav format (but are 
+	also included in the given workspaces). The sampling rate of each speech 
+	file is indicated in the file name. The Data directory for Chapter 13, 
+	for example, contains the required speech files:
+
+	speech1_10k.wav   speech_10k.wav
+	speech1_10k.pcm   speech_10k.pcm   
+
+	If the designated sampling is not supported by a desired platform, 
+	then in order to listen to the files, a change in sampling rate must 
+	be made (e.g., using MATLAB decimation and interpolation functions) 
+	for the particular platform.
+
+
+

Discrete_Time_Speech_SP_Quatieri/chapter10/Back/ex10_13_creaky.m

@@ -0,0 +1,6 @@
+
+DIR_IN = 'Data/';
+filename = 'silly_items.8k';
+
+display = 1;
+[pitch, voicing] = fread_pitch_creaky([DIR_IN, filename], display);

Discrete_Time_Speech_SP_Quatieri/chapter10/Back/ex10_13_diplo.m

@@ -0,0 +1,6 @@
+
+DIR_IN = 'Data/';
+filename = 'jazz_hour.8k';
+
+display = 1;
+[pitch, voicing] = fread_pitch_diplo([DIR_IN, filename], display);

Discrete_Time_Speech_SP_Quatieri/chapter10/Back/ex10_13_modulate.m

@@ -0,0 +1,6 @@
+
+DIR_IN = 'Data/';
+filename = 'NE1.mm.8k';
+
+display = 1;
+[pitch, voicing] = fread_pitch_modulate([DIR_IN, filename], display);

Discrete_Time_Speech_SP_Quatieri/chapter10/Back/ex10_13_speech1.m

@@ -0,0 +1,6 @@
+
+DIR_IN = 'Data/';
+filename = 'tfq.roy.8k';
+
+display = 1;
+[pitch, voicing] = fread_pitch_creaky([DIR_IN, filename], display);

Discrete_Time_Speech_SP_Quatieri/chapter10/Back/fread_pitch_creaky.m

@@ -0,0 +1,71 @@
+
+function [pitch, voicing] = fread_pitch(filename, display)
+%
+% [pitch, voicing] = fread_pitch(filename, display)
+%
+%
+% read pitch and voicing as floats
+%
+% filename is input filename
+% display = 0:plot; 1:noplot
+%
+%
+			% options
+			% open file
+	fid = fopen([filename '.pitch'],'r');
+
+			% write
+	[data, count] = fread(fid, 'float');
+
+	add_frm = 10;
+	add_on = add_frm*80;
+	data = [data' zeros(1,add_frm*2)]; 
+	lgh  = length(data);
+	n = 1:2:lgh;
+	pitch = data(n);
+	% pitch = 10*data(n);
+	n = 2:2:lgh;
+	voicing = data(n);
+
+
+	x = load24(filename);
+	x = x/max(abs(x));
+	x = [x' zeros(1, add_on)];
+	lghx = length(x);
+	x = [zeros(1, 160), x(1:lghx-160)];
+	lghx = length(x);
+	lghx_ms = lghx/80;
+
+	if display == 1
+		clf;
+		subplot(311)
+		plot((1:lghx)/8000, x)
+		axis([ 0 lghx_ms/100 -1.25 1.25])
+		ylabel('Amplitude')
+		title('(a)')
+		grid
+
+		n = (1:lgh/2);
+		subplot(312)
+		plot(n/100, pitch(1:lgh/2))
+		axis([0 lgh/2/100 0 450])
+		ylabel('Freq (Hz)')
+		title('(b)')
+		%title('PITCH')
+		grid
+		subplot(313)
+		plot(n/100, voicing(1:lgh/2))
+		axis([ 0 lgh/2/100 0 1.5])
+		%title('VOICING')
+		title('(c)')
+		grid
+		xlabel('Time (s)')
+		ylabel('Probability')
+		pause(.5)
+	end;
+
+
+	fclose(fid);
+
+
+

Discrete_Time_Speech_SP_Quatieri/chapter10/Back/fread_pitch_diplo.m

@@ -0,0 +1,71 @@
+
+function [pitch, voicing] = fread_pitch(filename, display)
+%
+% [pitch, voicing] = fread_pitch(filename, display)
+%
+%
+% read pitch and voicing as floats
+%
+% filename is input filename
+% display = 0:plot; 1:noplot
+%
+%
+			% options
+			% open file
+	fid = fopen([filename '.pitch'],'r');
+
+			% write
+	[data, count] = fread(fid, 'float');
+
+	add_frm = 10;
+	add_on = add_frm*80;
+	data = [data' zeros(1,add_frm*2)]; 
+	lgh  = length(data);
+	n = 1:2:lgh;
+	pitch = data(n);
+	% pitch = 10*data(n);
+	n = 2:2:lgh;
+	voicing = data(n);
+
+
+	x = load24(filename);
+	x = x/max(abs(x));
+	x = [x' zeros(1, add_on)];
+	lghx = length(x);
+	x = [zeros(1, 160), x(1:lghx-160)];
+	lghx = length(x);
+	lghx_ms = lghx/80;
+
+	if display == 1
+		clf;
+		subplot(311)
+		plot((1:lghx)/8000, x)
+		axis([ 0 lghx_ms/100 -1.25 1.25])
+		ylabel('Amplitude')
+		title('(a)')
+		grid
+
+		n = (1:lgh/2);
+		subplot(312)
+		plot(n/100, pitch(1:lgh/2))
+		axis([0 lgh/2/100 0 175])
+		ylabel('Freq (Hz)')
+		title('(b)')
+		%title('PITCH')
+		grid
+		subplot(313)
+		plot(n/100, voicing(1:lgh/2))
+		axis([ 0 lgh/2/100 0 1.5])
+		%title('VOICING')
+		title('(c)')
+		grid
+		xlabel('Time (s)')
+		ylabel('Probability')
+		pause(.5)
+	end;
+
+
+	fclose(fid);
+
+
+

Discrete_Time_Speech_SP_Quatieri/chapter10/Back/fread_pitch_modulate.m

@@ -0,0 +1,71 @@
+
+function [pitch, voicing] = fread_pitch(filename, display)
+%
+% [pitch, voicing] = fread_pitch(filename, display)
+%
+%
+% read pitch and voicing as floats
+%
+% filename is input filename
+% display = 0:plot; 1:noplot
+%
+%
+			% options
+			% open file
+	fid = fopen([filename '.pitch'],'r');
+
+			% write
+	[data, count] = fread(fid, 'float');
+
+	add_frm = 10;
+	add_on = add_frm*80;
+	data = [data' zeros(1,add_frm*2)]; 
+	lgh  = length(data);
+	n = 1:2:lgh;
+	pitch = data(n);
+	% pitch = 10*data(n);
+	n = 2:2:lgh;
+	voicing = data(n);
+
+
+	x = load24(filename);
+	x = x/max(abs(x));
+	x = [x' zeros(1, add_on)];
+	lghx = length(x);
+	x = [zeros(1, 160), x(1:lghx-160)];
+	lghx = length(x);
+	lghx_ms = lghx/80;
+
+	if display == 1
+		clf;
+		subplot(311)
+		plot((1:lghx)/8000, x)
+		axis([ 0 lghx_ms/100 -1.25 1.25])
+		ylabel('Amplitude')
+		title('(a)')
+		grid
+
+		n = (1:lgh/2);
+		subplot(312)
+		plot(n/100, pitch(1:lgh/2))
+		axis([0 lgh/2/100 0 650])
+		ylabel('Freq (Hz)')
+		title('(b)')
+		%title('PITCH')
+		grid
+		subplot(313)
+		plot(n/100, voicing(1:lgh/2))
+		axis([ 0 lgh/2/100 0 1.5])
+		%title('VOICING')
+		title('(c)')
+		grid
+		xlabel('Time (s)')
+		ylabel('Probability')
+		pause(.5)
+	end;
+
+
+	fclose(fid);
+
+
+

Discrete_Time_Speech_SP_Quatieri/chapter10/Back/fread_pitch_speech1.m

@@ -0,0 +1,71 @@
+
+function [pitch, voicing] = fread_pitch(filename, display)
+%
+% [pitch, voicing] = fread_pitch(filename, display)
+%
+%
+% read pitch and voicing as floats
+%
+% filename is input filename
+% display = 0:plot; 1:noplot
+%
+%
+			% options
+			% open file
+	fid = fopen([filename '.pitch'],'r');
+
+			% write
+	[data, count] = fread(fid, 'float');
+
+	add_frm = 10;
+	add_on = add_frm*80;
+	data = [data' zeros(1,add_frm*2)]; 
+	lgh  = length(data);
+	n = 1:2:lgh;
+	pitch = data(n);
+	% pitch = 10*data(n);
+	n = 2:2:lgh;
+	voicing = data(n);
+
+
+	x = load24(filename);
+	x = x/max(abs(x));
+	x = [x' zeros(1, add_on)];
+	lghx = length(x);
+	x = [zeros(1, 160), x(1:lghx-160)];
+	lghx = length(x);
+	lghx_ms = lghx/80;
+
+	if display == 1
+		clf;
+		subplot(311)
+		plot((1:lghx)/8000, x)
+		axis([ 0 lghx_ms/100 -1.25 1.25])
+		ylabel('Amplitude')
+		title('(a)')
+		grid
+
+		n = (1:lgh/2);
+		subplot(312)
+		plot(n/100, pitch(1:lgh/2))
+		axis([0 lgh/2/100 0 175])
+		ylabel('Freq (Hz)')
+		title('(b)')
+		%title('PITCH')
+		grid
+		subplot(313)
+		plot(n/100, voicing(1:lgh/2))
+		axis([ 0 lgh/2/100 0 1.5])
+		%title('VOICING')
+		title('(c)')
+		grid
+		xlabel('Time (s)')
+		ylabel('Probability')
+		pause(.5)
+	end;
+
+
+	fclose(fid);
+
+
+

Discrete_Time_Speech_SP_Quatieri/chapter10/Data/README

@@ -0,0 +1,9 @@
+
+
+Speech equivalences:
+
+speech1_8k.pcm    = tfq.roy.8k
+
+diplo1_8k.pcm     = jazz_hour.8k
+creak1_8k.pcm     = silly_items.8k
+modulated1_8k.pcm = NE1.mm.8k

Discrete_Time_Speech_SP_Quatieri/chapter10/ex10_13_creaky.m

@@ -0,0 +1,6 @@
+
+DIR_IN = 'Data/';
+filename = 'silly_items.8k';
+
+display = 1;
+[pitch, voicing] = fread_pitch_creaky([DIR_IN, filename], display);