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

# © 2016 and later: Unicode, Inc. and others.
# License & terms of use: http://www.unicode.org/copyright.html#License
#
# File: zu_zu_FONIPA.txt
# Generated from CLDR
#

# Pronunciation rules for isiZulu.
#
# Author: mjansche@google.com (Martin Jansche)
#
# These rules transcribe isiZulu 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 isiZulu pronunciation dictionary
# (http://rma.nwu.ac.za/index.php/resource-catalogue/nchlt-inlang-dictionaries.html).
# They correctly account for all 15,000 entries in the dictionary.
#
# The NCHLT 2013 phone set 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 (depressor) clicks, e.g. ɡ\u0361ǀ instead of ɡǀ, to
# avoid ambiguity and make the phoneme inventory uniquely decodable.
::Lower;
tsh → t\u0361ʃʼ;
bh → b;
ch → ǀʰ;
dl → ɮ;
gc → ɡ\u0361ǀ;
gq → ɡ\u0361ǃ;
gx → ɡ\u0361ǁ;
hh → ɦ;  # To investigate: /ɦ/ and /h/ may be switched in the NCHLT dictionary.
hl → ɬ;
kh → kʰ;
kl → k\u0361ɬ;
ny → ɲ;
ph → pʰ;
qh → ǃʰ;
n { sh → t\u0361sʼ;
sh → ʃ;
th → tʰ;
xh → ǁʰ;
a → a;
m { b → b;
b → ɓ;
c → ǀ;
d → d;
e → ɛ;
f → f;
g → ɡ;
h → h;
i → i;
j → d\u0361ʒ;
k → k;
l → l;
m → m;
[$] { n } gc → n;
n } [gk] → ŋ;
n } j → ɲ;
n → n;
o → ɔ;
p → pʼ;
q → ǃ;
n { s → t\u0361sʼ;
s → s;
t → tʼ;
u → u;
v → v;
w → w;
x → ǁ;
y → j;
n { z → d\u0361z;
z → z;
Commit	Line	Data
f3c0d7a5 A	1	# © 2016 and later: Unicode, Inc. and others.
	2	# License & terms of use: http://www.unicode.org/copyright.html#License
	3	#
2ca993e8	4	# File: zu_zu_FONIPA.txt
f3c0d7a5	5	# Generated from CLDR
2ca993e8 A	6	#
	7
	8	# Pronunciation rules for isiZulu.
	9	#
	10	# Author: mjansche@google.com (Martin Jansche)
	11	#
	12	# These rules transcribe isiZulu into the phoneme inventory used within the
	13	# NCHLT Speech Corpus (https://sites.google.com/site/nchltspeechcorpus/home).
	14	#
	15	# The rules were tested using the NCHLT-inlang isiZulu pronunciation dictionary
	16	# (http://rma.nwu.ac.za/index.php/resource-catalogue/nchlt-inlang-dictionaries.html).
	17	# They correctly account for all 15,000 entries in the dictionary.
	18	#
	19	# The NCHLT 2013 phone set does not indicate tone in any way. Transcription of
	20	# tone is out of scope without a dictionary, since tone is generally not
	21	# indicated in the orthography. Nasal clicks are not treated as separated
	22	# phonemes in the NCHLT 2013 phone set and are transcribed as a sequence of
	23	# nasal plus click instead.
	24	#
	25	# One minor notational deviation from the NCHLT 2013 phone set is that we use a
	26	# tie bar within the complex (depressor) clicks, e.g. ɡ\u0361ǀ instead of ɡǀ, to
	27	# avoid ambiguity and make the phoneme inventory uniquely decodable.
	28	::Lower;
	29	tsh → t\u0361ʃʼ;
	30	bh → b;
	31	ch → ǀʰ;
	32	dl → ɮ;
	33	gc → ɡ\u0361ǀ;
	34	gq → ɡ\u0361ǃ;
	35	gx → ɡ\u0361ǁ;
	36	hh → ɦ; # To investigate: /ɦ/ and /h/ may be switched in the NCHLT dictionary.
	37	hl → ɬ;
	38	kh → kʰ;
	39	kl → k\u0361ɬ;
	40	ny → ɲ;
	41	ph → pʰ;
	42	qh → ǃʰ;
	43	n { sh → t\u0361sʼ;
	44	sh → ʃ;
	45	th → tʰ;
	46	xh → ǁʰ;
	47	a → a;
	48	m { b → b;
	49	b → ɓ;
	50	c → ǀ;
	51	d → d;
	52	e → ɛ;
	53	f → f;
	54	g → ɡ;
	55	h → h;
	56	i → i;
	57	j → d\u0361ʒ;
	58	k → k;
	59	l → l;
	60	m → m;
	61	[$] { n } gc → n;
	62	n } [gk] → ŋ;
	63	n } j → ɲ;
	64	n → n;
	65	o → ɔ;
	66	p → pʼ;
	67	q → ǃ;
	68	n { s → t\u0361sʼ;
	69	s → s;
70	t → tʼ;
71	u → u;
72	v → v;
73	w → w;
74	x → ǁ;
75	y → j;
76	n { z → d\u0361z;
77	z → z;
78