89 lines
2.2 KiB
XML
89 lines
2.2 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="zu" target="zu_FONIPA" direction="forward" alias="zu-fonipa-t-zu">
|
||
<tRule><![CDATA[
|
||
# 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. ɡ͡ǀ instead of ɡǀ, to
|
||
# avoid ambiguity and make the phoneme inventory uniquely decodable.
|
||
|
||
::Lower;
|
||
|
||
tsh → t͡ʃʼ;
|
||
|
||
bh → b;
|
||
ch → ǀʰ;
|
||
dl → ɮ;
|
||
gc → ɡ͡ǀ;
|
||
gq → ɡ͡ǃ;
|
||
gx → ɡ͡ǁ;
|
||
hh → ɦ; # To investigate: /ɦ/ and /h/ may be switched in the NCHLT dictionary.
|
||
hl → ɬ;
|
||
kh → kʰ;
|
||
kl → k͡ɬ;
|
||
ny → ɲ;
|
||
ph → pʰ;
|
||
qh → ǃʰ;
|
||
n { sh → t͡sʼ;
|
||
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 → d͡ʒ;
|
||
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 → t͡sʼ;
|
||
s → s;
|
||
t → tʼ;
|
||
u → u;
|
||
v → v;
|
||
w → w;
|
||
x → ǁ;
|
||
y → j;
|
||
n { z → d͡z;
|
||
z → z;
|
||
]]></tRule>
|
||
</transform>
|
||
</transforms>
|
||
</supplementalData>
|