pronounce 0.0.1

data/data/beep/lexicode.doc

@@ -0,0 +1,47 @@
+This file documents the code used to represent the word forms in the lexicon
+
+The valid characters in this field are:
+
+Characters	Notes						Example
+[A-Z]	All words are presently in upper case			AARDVARK
+.	Abbreviations are represented with a trailing '.'	A.
+-	Hypenated words are seaprated by '-'			A-BOMB
+_	Separator for multiple words with one lexical entry	A_PRIORI
+'								ACCOUNTANTS'
+\'								CAF\'E
+\`								CR\`ECHE
+\^								AR\^ETE
+								
+
+Also there are these one-off words:
+
+!EXCLAMATION-POINT
+"DOUBLE-QUOTE
+%PERCENT
+&AMPERSAND
+&EM
+...
+&UN
+
+'EM
+...
+'UN
+(LEFT-PAREN
+)RIGHT-PAREN
++PLUS
+,COMMA
+--DASH
+-HYPHEN
+-SHIRE
+...ELLIPSIS
+.PERIOD
+.POINT
+/SLASH
+:COLON
+;SEMI-COLON
+;SEMI-COLON
+;SEMICOLON
+?QUESTION-MARK
+...
+{LEFT-BRACE
+}RIGHT-BRACE

data/data/beep/phoncode.doc

@@ -0,0 +1,48 @@
+ARPAbet	MRPA	Edin.	Alvey		Example		Relative frequency
+p	p	p	p		put		3.1%
+b	b	b	b		but		2.3%
+t	t	t	t		ten		6.8%
+d	d	d	d		den		4.1%
+k	k	k	k		can		4.7%
+m	m	m	m		man		3.1%
+n	n	n	n		not		6.5%
+l	l	l	l		like		5.5%
+r	r	r	r		run		5.4%
+f	f	f	f		full		1.8%
+v	v	v	v		very		1.2%
+s	s	s	s		some		6.6%
+z	z	z	z		zeal		3.6%
+hh	h	h	h		hat		0.8%
+w	w	w	w		went		0.9%
+g	g	g	g		game		1.3%
+ch	ch	ch	tS		chain		0.5%
+jh	jh	j	dZ		Jane		0.8%
+ng	ng	ng	9		long		1.6%
+th	th	th	T		thin		0.3%
+dh	dh	dh	D		then		12.2%
+sh	sh	sh	S		ship		1.2%
+zh	zh	zh	Z		measure		0.1%
+y	y	y	j		yes		0.8%
+iy	ii	ee	i		bean		1.4%
+aa	aa	ar	A		barn		0.9%
+ao	oo	aw	O		born		1.0%
+uw	uu	uu	u		boon		1.0%
+er	@@	er	3		burn		0.7%
+ih	i	i	I		pit		10.0%
+eh	e	e	e		pet		2.4%
+ae	a	aa	&		pat		2.5%
+ah	uh	u	V		putt		1.5%
+oh	o	o	0		pot		1.6%
+uh	u	oo	U		good		0.4%
+ax	@	a	@		about		7.2%
+ey	ei	ai	eI		bay		2.0%
+ay	ai	ie	aI		buy		1.6%
+oy	oi	oi	oI		boy		0.2%
+ow	ou	oa	@U		no		1.5%
+aw	au	ou	aU		now		0.4%
+ia	i@	eer	I@		peer		0.7%
+ea	e@	air	e@		pair		0.2%
+ua	u@	oor	U@		poor		0.2%
+
+See also the files abvailable from the Oxford Text Archive by FTP from
+sable.ox.ac.uk in directories /pub/ota/public/dicts/710 and 1054.

data/data/beep/phone45.tab

@@ -0,0 +1,45 @@
+sil
+aa
+ae
+ah
+ao
+aw
+ax
+ay
+b
+ch
+d
+dh
+ea
+eh
+er
+ey
+f
+g
+hh
+ia
+ih
+iy
+jh
+k
+l
+m
+n
+ng
+oh
+ow
+oy
+p
+r
+s
+sh
+t
+th
+ua
+uh
+uw
+v
+w
+y
+z
+zh

data/data/beep/sayTimit.doc

@@ -0,0 +1,130 @@
+'sayTimit' is a util. to check/develop transcription dictionaries in the "beep"
+notation, using 'say' from rsynth to produce audial checking of the transcrip-
+tion. To save time, 'say' is invoked as the destination of a UNIX pipe, and 
+info is fed to it under certain commands. No attempt is made to make use of 
+the stress markers (this is due to rsynth, not the utility...).
+
+Commands are given to say the current transcription, say arbitrary text, look
+up the current word in a dictionary &c.
+
+--------------------------------------------------------------------------------
+instructions.
+--------------------------------------------------------------------------------
+
+
+Basic instructions
+------------------
+
+usage> sayTimit <dict file> [<start place>]
+
+dict file is assumed in a format like:
+
+LACKLUSTER       l ae1 k l ah2 s t ax axr	# comment.
+LAKEFIELD        l ey1 k f iy2 l d
+
+ie, the word; the timit transcription, and an optional comment. 
+
+"start place" is a word which should be in the file; this just allows you
+to start work in the middle of a file, if something went wrong on a previous
+run &c &c. 
+
+Before running - you need to determine how 'say' (from rsynth) is to be run.
+Just change line that looks like:
+
+> open(SAY, "| <say-command>");                   # crank up 'say'.
+
+eg, "say +h -g 0.2" set the gain (volume) to 20%, and sends the sound to the 
+headphone port. Additionally, the port and gain are controllable on SUNs with 
+the 'gaintool' program which is part of the SunOS SOUND demonstration package
+(have a look in /usr/demo/SOUND on your machine). 
+
+
+Using it.
+--------
+
+eg on the line for 
+LACKLUSTER       l ae1 k l ah2 s t ax axr       # comment.
+
+the following is shown: the current line and the translation into ota phonemes.
+
+>> LACKLUSTER       l ae1 k l ah2 s t ax axr
+== l'&kl,Vst@R
+
+The control is a loop which only exits on 'n'.
+
+* hitting return will 'say' the transcription (in ota format)
+* hitting n <+cr> goes to the next line in the dict.
+* s <text> sends the text verbatim to 'say' - eg you might want to listen to 
+  	a similar word:  			s duster
+	or try a different transcription: 	s [lVst3]
+
+* t <text> makes the current line 'text' - eg can edit the dict file in a 
+	separate window, and paste in a version to try. 
+
+* p retrieves the previous version of the current line (ie, before you used 't')
+ 
+
+'sayTimit' is a util. to check/develop transcription dictionaries in the "beep"
+notation, using 'say' from rsynth to produce audial checking of the transcrip-
+tion. To save time, 'say' is invoked as the destination of a UNIX pipe, and 
+info is fed to it under certain commands. No attempt is made to make use of 
+the stress markers (this is due to rsynth, not the utility...).
+
+Commands are given to say the current transcription, say arbitrary text, look
+up the current word in a dictionary &c.
+
+--------------------------------------------------------------------------------
+instructions.
+--------------------------------------------------------------------------------
+
+
+Basic instructions
+------------------
+
+usage> sayTimit <dict file> [<start place>]
+
+dict file is assumed in a format like:
+
+LACKLUSTER       l ae1 k l ah2 s t ax axr	# comment.
+LAKEFIELD        l ey1 k f iy2 l d
+
+ie, the word; the timit transcription, and an optional comment. 
+
+"start place" is a word which should be in the file; this just allows you
+to start work in the middle of a file, if something went wrong on a previous
+run &c &c. 
+
+Before running - you need to determine how 'say' (from rsynth) is to be run.
+Just change line that looks like:
+
+> open(SAY, "| <say-command>");                   # crank up 'say'.
+
+eg, "say +h -g 0.2" set the gain (volume) to 20%, and sends the sound to the 
+headphone port. Additionally, the port and gain are controllable on SUNs with 
+the 'gaintool' program which is part of the SunOS SOUND demonstration package
+(have a look in /usr/demo/SOUND on your machine). 
+
+
+Using it.
+--------
+
+eg on the line for 
+LACKLUSTER       l ae1 k l ah2 s t ax axr       # comment.
+
+the following is shown: the current line and the translation into ota phonemes.
+
+>> LACKLUSTER       l ae1 k l ah2 s t ax axr
+== l'&kl,Vst@R
+
+The control is a loop which only exits on 'n'.
+
+* hitting return will 'say' the transcription (in ota format)
+* hitting n <+cr> goes to the next line in the dict.
+* s <text> sends the text verbatim to 'say' - eg you might want to listen to 
+  	a similar word:  			s duster
+	or try a different transcription: 	s [lVst3]
+
+* t <text> makes the current line 'text' - eg can edit the dict file in a 
+	separate window, and paste in a version to try. 
+
+* p retrieves the previous version of the current line (ie, before you used 't')

data/data/beep/sayTimit.pl

@@ -0,0 +1,174 @@
+#! /usr/local/bin/perl
+
+# sayTimit
+
+# Paul Callaghan, may1994.
+# University of Durham.
+
+# instructions elsewhere (in file sayTimit.doc)
+
+%timit2ota = (
+"b", "b",     
+"d", "d",     
+"g", "g",     
+"p", "p",     
+"t", "t",     
+"k", "k",     
+"dx", "d",    
+"q", "t",     
+
+
+"jh", "dZ",    
+"ch", "tS",    
+
+
+"s", "s",     
+"sh", "S",    
+"z", "z",     
+"zh", "Z",    
+"f", "f",     
+"th", "T",    
+"v", "v",     
+"dh", "D",    
+
+
+"m", "m",     
+"n", "n",     
+"ng", "N",    
+"em", "m",    
+"en", "n",    
+"eng", "N",   
+"nx", "n",    
+
+
+
+"l", "l",     
+"r", "r",     
+"w", "w",     
+"y", "j",     
+"hh", "h",    
+"hv", "h",    
+"el", "l",    
+
+
+
+
+"iy", "i",    
+"ih", "I",    
+"eh", "e",    
+
+"ea", "e@",				# eg bare, or air. 
+"ey", "eI",    
+"ae", "&",    
+"aa", "A",    
+"aw", "aU",    
+"ay", "aI",    
+"ah", "V",    
+
+"oh", "0",    
+"oy", "oI",    
+"ow", "@U",    
+"uh", "U",    
+"uw", "u",    
+"ux", "u",    
+
+"er", "3",    
+"ax", "@",    
+"ix", "I",    
+"axr", "R",   
+"ax-h", "e",				# forgotten what this is!
+					# non-timit symbols for RP Vowels
+"ia", "I@",					# as in 'beer'
+"ao", "O",					# as in 'cord'
+"ua", "U@",					# as in 'tour'
+
+"epi", " ",					# epenthetic silence
+"sil", " ",					# silence
+"pau", " ",					# pause
+
+"1", "'",					# primary stress
+"2", ","					# secondary stress.
+	  );
+
+################################################################################
+# crank up 'say'.
+
+# "say:sound <params>" needs to be changed to your installation of
+# rsynth, with desired parameters.
+
+open(SAY, "| say:sound +h -g 0.2") || die "Couldn't start SAY: $!\n";	
+
+# then make it flush after every write/print operation. The method is to
+# set it temporarily as the default output channel, then get it to flush,
+# then reset the old default channel. Surprisingly (for some ppl), SAY will
+# STILL flush as required. 
+
+$oldofh = select(SAY);				# make it default 
+$| = 1;						# flush after each IO op.
+select($oldofh);				# and reset.
+
+
+# open input file.
+
+open(INPUT, $ARGV[0]) || die "Couldn't open pronunciations file $ARGV[0].\n";
+shift;
+
+# startfrom word? 
+$startfrom = $ARGV[0];
+
+if ($startfrom ne "") {
+	do {
+		$_ = <INPUT>;
+		@tmp = split;
+	} until ( $tmp[0] eq $startfrom);
+	print "startfrom " . $_ . "\n";
+		
+} else {
+	$_ = <INPUT>;		# first line expected 
+}
+	
+
+# main loop.
+
+START:
+do {
+	$orig = $_;
+	s/#.*//;				# kill comment
+	s/[.]//g;				# kill '.' 
+
+	s/([a-z]*)1/1 \1/g;
+	s/([a-z]*)2/2 \1/g;			
+				# change stress notation: OTA seems to require
+				# marks BEFORE the syllable, not AFTER the
+				# 'nuclear'(?) vowel.
+
+	@tmp = split;
+
+	$phons = "";
+	foreach $p (@tmp[1..$#tmp]) {
+		if ($timit2ota{$p} eq "") {
+			print "\nERROR: unknown symbol " . $p;
+		} else {
+			$phons .= $timit2ota{$p};
+		}
+	}
+	$tmp[0] =~ tr/A-Z/a-z/;		# current word to lower case.
+
+	$ig = 0;
+	do {
+		print STDOUT ">> " . $orig;
+		print STDOUT "== " . $phons . "\n";
+		unless ($ig) { print SAY "[" . $phons . "]\n"; }
+						# write result to SAY
+		$ig = 0;
+		$cmd = <STDIN>;
+		chop $cmd;
+		if ($cmd =~ /^s/) { $cmd =~ s/^s//; if ($cmd eq "") { print SAY $tmp[0] . "\n"; } else { print SAY $cmd . "\n"; } $ig = 1;}
+		if ($cmd =~ /^t /) { $old = $_; $cmd =~ s/^t //; $_ = $cmd; goto START; }
+		if ($cmd =~ /^p/) { $_ = $old; goto START; }
+
+	} until ($cmd eq "n");
+} while (<INPUT>);	
+
+close(INPUT);
+close(SAY);

data/data/cmudict/00README_FIRST.txt

@@ -0,0 +1,36 @@
+
+CMUdict
+-------
+
+CMUdict (the Carnegie Mellon Pronouncing Dictionary) is a free
+pronouncing dictionary of English, suitable for uses in speech
+technology and is maintained by the Speech Group in the School of
+Computer Science at Carnegie Mellon University.
+
+The Carnegie Mellon Speech Group does not guarantee the accuracy of
+this dictionary, nor its suitability for any specific purpose. In
+fact, we expect a number of errors, omissions and inconsistencies to
+remain in the dictionary. We intend to continually update the
+dictionary by correction existing entries and by adding new ones. From
+time to time a new major version will be released.
+
+We welcome input from users: Please send email to Alex Rudnicky
+(air+cmudict@cs.cmu.edu).
+
+The Carnegie Mellon Pronouncing Dictionary, in its current and
+previous versions is Copyright (C) 1993-2008 by Carnegie Mellon
+University.  Use of this dictionary for any research or commercial
+purpose is completely unrestricted.  If you make use of or
+redistribute this material we request that you acknowledge its
+origin in your descriptions.
+
+If you add words to or correct words in your version of this
+dictionary, we would appreciate it if you could send these additions
+and corrections to us (air+cmudict@cs.cmu.edu) for consideration in a
+subsequent version. All submissions will be reviewed and approved by
+the current maintainer, Alex Rudnicky at Carnegie Mellon.
+
+------------------------------------------------------------------
+The current version of cmudict is cmudict.0.7a 
+[First released October 29, 2007]
+