[apple/icu.git] / icuSources / data / translit / xh_xh_FONIPA.txt

# ***************************************************************************
# *
# *  Copyright (C) 2004-2016, International Business Machines
# *  Corporation; Unicode, Inc.; and others.  All Rights Reserved.
# *
# ***************************************************************************
# File: xh_xh_FONIPA.txt
# Generated from CLDR 
#

# Pronunciation rules for isiXhosa.
#
# Author: mjansche@google.com (Martin Jansche)
#
# These rules transcribe isiXhosa into the phoneme inventory used within the
# NCHLT Speech Corpus (https://sites.google.com/site/nchltspeechcorpus/home).
#
# The rules were tested using the NCHLT-inlang isiXhosa pronunciation dictionary
# (http://rma.nwu.ac.za/index.php/resource-catalogue/nchlt-inlang-dictionaries.html).
# They correctly account for 14,999 out of 15,000 entries in the dictionary.
#
# The NCHLT 2013 phone set does not distinguish short and long vowels and does
# not indicate tone in any way. Transcription of tone is out of scope without a
# dictionary, since tone is generally not indicated in the orthography. Nasal
# clicks are not treated as separated phonemes in the NCHLT 2013 phone set and
# are transcribed as a sequence of nasal plus click instead.
#
# One minor notational deviation from the NCHLT 2013 phone set is that we use a
# tie bar within the complex (slack voiced) clicks, e.g. ɡ\u0361ǀ instead of ɡǀ, to
# avoid ambiguity and make the phoneme inventory uniquely decodable.
::Lower;
nyh → ɲʰ;
n { tsh → t\u0361ʃʼ;
tsh → t\u0361ʃʰ;
tyh → cʰ;
bh → bʰ;
ch → ǀʰ;
dl → ɮ;
dy → ɟ;
gc → ɡ\u0361ǀ;
gq → ɡ\u0361ǃ;
gr → ɣ;
gx → ɡ\u0361ǁ;
hl → ɬ;
kh → kʰ;
kr → k\u0361x;
mh } [^l] → mʰ;  # <mhl> denotes /mɬ/ instead
nh → nʰ;
ny → ɲ;
ph → pʰ;
qh → ǃʰ;
sh → ʃ;
th → tʰ;
tl → t\u0361ɬʼ;
ts → t\u0361sʼ;
ty → cʼ;
xh → ǁʰ;
aa → | a;
ee → | e;
ii → | i;
kc → | c;
kq → | q;
mm → | m;
oo → | o;
rh → | r;
uu → | u;
a → a;
b → ɓ;
c → ǀ;
d → d;
e → ɛ;
f → f;
g → ɡ;
h → h;
i → i;
j → d\u0361ʒ;
k → kʼ;
l → l;
m → m;
n } g → ŋ;
n → n;
o → ɔ;
p → pʼ;
q → ǃ;
r → r;
s → s;
t → tʼ;
u → u;
v → v;
w → w;
x → ǁ;
y → j;
z → z;
Commit	Line	Data
2ca993e8 A	1	# ***************************************************************************
	2	# *
	3	# * Copyright (C) 2004-2016, International Business Machines
	4	# * Corporation; Unicode, Inc.; and others. All Rights Reserved.
	5	# *
	6	# ***************************************************************************
	7	# File: xh_xh_FONIPA.txt
	8	# Generated from CLDR
	9	#
	10
	11	# Pronunciation rules for isiXhosa.
	12	#
	13	# Author: mjansche@google.com (Martin Jansche)
	14	#
	15	# These rules transcribe isiXhosa into the phoneme inventory used within the
	16	# NCHLT Speech Corpus (https://sites.google.com/site/nchltspeechcorpus/home).
	17	#
	18	# The rules were tested using the NCHLT-inlang isiXhosa pronunciation dictionary
	19	# (http://rma.nwu.ac.za/index.php/resource-catalogue/nchlt-inlang-dictionaries.html).
	20	# They correctly account for 14,999 out of 15,000 entries in the dictionary.
	21	#
	22	# The NCHLT 2013 phone set does not distinguish short and long vowels and does
	23	# not indicate tone in any way. Transcription of tone is out of scope without a
	24	# dictionary, since tone is generally not indicated in the orthography. Nasal
	25	# clicks are not treated as separated phonemes in the NCHLT 2013 phone set and
	26	# are transcribed as a sequence of nasal plus click instead.
	27	#
	28	# One minor notational deviation from the NCHLT 2013 phone set is that we use a
	29	# tie bar within the complex (slack voiced) clicks, e.g. ɡ\u0361ǀ instead of ɡǀ, to
	30	# avoid ambiguity and make the phoneme inventory uniquely decodable.
	31	::Lower;
	32	nyh → ɲʰ;
	33	n { tsh → t\u0361ʃʼ;
	34	tsh → t\u0361ʃʰ;
	35	tyh → cʰ;
	36	bh → bʰ;
	37	ch → ǀʰ;
	38	dl → ɮ;
	39	dy → ɟ;
	40	gc → ɡ\u0361ǀ;
	41	gq → ɡ\u0361ǃ;
	42	gr → ɣ;
	43	gx → ɡ\u0361ǁ;
	44	hl → ɬ;
	45	kh → kʰ;
	46	kr → k\u0361x;
	47	mh } [^l] → mʰ; # <mhl> denotes /mɬ/ instead
	48	nh → nʰ;
	49	ny → ɲ;
	50	ph → pʰ;
	51	qh → ǃʰ;
	52	sh → ʃ;
	53	th → tʰ;
	54	tl → t\u0361ɬʼ;
	55	ts → t\u0361sʼ;
	56	ty → cʼ;
	57	xh → ǁʰ;
	58	aa → \| a;
	59	ee → \| e;
	60	ii → \| i;
	61	kc → \| c;
	62	kq → \| q;
	63	mm → \| m;
	64	oo → \| o;
65	rh → \| r;
66	uu → \| u;
67	a → a;
68	b → ɓ;
69	c → ǀ;
70	d → d;
71	e → ɛ;
72	f → f;
73	g → ɡ;
74	h → h;
75	i → i;
76	j → d\u0361ʒ;
77	k → kʼ;
78	l → l;
79	m → m;
80	n } g → ŋ;
81	n → n;
82	o → ɔ;
83	p → pʼ;
84	q → ǃ;
85	r → r;
86	s → s;
87	t → tʼ;
88	u → u;
89	v → v;
90	w → w;
91	x → ǁ;
92	y → j;
93	z → z;
94