103 lines
2.4 KiB
XML
103 lines
2.4 KiB
XML
<?xml version="1.0" encoding="UTF-8" ?>
|
||
<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
|
||
<!-- Copyright © 1991-2015 Unicode, Inc.
|
||
CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)
|
||
For terms of use, see http://www.unicode.org/copyright.html -->
|
||
<supplementalData>
|
||
<version number="$Revision$" />
|
||
<transforms>
|
||
<transform source="xh" target="xh_FONIPA" direction="forward" alias="xh-fonipa-t-xh">
|
||
<tRule><![CDATA[
|
||
# 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. ɡ͡ǀ instead of ɡǀ, to
|
||
# avoid ambiguity and make the phoneme inventory uniquely decodable.
|
||
|
||
::Lower;
|
||
|
||
nyh → ɲʰ;
|
||
n { tsh → t͡ʃʼ;
|
||
tsh → t͡ʃʰ;
|
||
tyh → cʰ;
|
||
|
||
bh → bʰ;
|
||
ch → ǀʰ;
|
||
dl → ɮ;
|
||
dy → ɟ;
|
||
gc → ɡ͡ǀ;
|
||
gq → ɡ͡ǃ;
|
||
gr → ɣ;
|
||
gx → ɡ͡ǁ;
|
||
hl → ɬ;
|
||
kh → kʰ;
|
||
kr → k͡x;
|
||
mh } [^l] → mʰ; # <mhl> denotes /mɬ/ instead
|
||
nh → nʰ;
|
||
ny → ɲ;
|
||
ph → pʰ;
|
||
qh → ǃʰ;
|
||
sh → ʃ;
|
||
th → tʰ;
|
||
tl → t͡ɬʼ;
|
||
ts → t͡sʼ;
|
||
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 → d͡ʒ;
|
||
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;
|
||
]]></tRule>
|
||
</transform>
|
||
</transforms>
|
||
</supplementalData>
|