]> git.saurik.com Git - apple/icu.git/blob - icuSources/data/translit/xh_xh_FONIPA.txt
ICU-62107.0.1.tar.gz
[apple/icu.git] / icuSources / data / translit / xh_xh_FONIPA.txt
1 # © 2016 and later: Unicode, Inc. and others.
2 # License & terms of use: http://www.unicode.org/copyright.html#License
3 #
4 # File: xh_xh_FONIPA.txt
5 # Generated from CLDR
6 #
7
8 # Pronunciation rules for isiXhosa.
9 #
10 # Author: mjansche@google.com (Martin Jansche)
11 #
12 # These rules transcribe isiXhosa 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 isiXhosa pronunciation dictionary
16 # (http://rma.nwu.ac.za/index.php/resource-catalogue/nchlt-inlang-dictionaries.html).
17 # They correctly account for 14,999 out of 15,000 entries in the dictionary.
18 #
19 # The NCHLT 2013 phone set does not distinguish short and long vowels and does
20 # not indicate tone in any way. Transcription of tone is out of scope without a
21 # dictionary, since tone is generally not indicated in the orthography. Nasal
22 # clicks are not treated as separated phonemes in the NCHLT 2013 phone set and
23 # are transcribed as a sequence of 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 (slack voiced) clicks, e.g. ɡ\u0361ǀ instead of ɡǀ, to
27 # avoid ambiguity and make the phoneme inventory uniquely decodable.
28 ::Lower;
29 nyh → ɲʰ;
30 n { tsh → t\u0361ʃʼ;
31 tsh → t\u0361ʃʰ;
32 tyh → cʰ;
33 bh → bʰ;
34 ch → ǀʰ;
35 dl → ɮ;
36 dy → ɟ;
37 gc → ɡ\u0361ǀ;
38 gq → ɡ\u0361ǃ;
39 gr → ɣ;
40 gx → ɡ\u0361ǁ;
41 hl → ɬ;
42 kh → kʰ;
43 kr → k\u0361x;
44 mh } [^l] → mʰ; # <mhl> denotes /mɬ/ instead
45 nh → nʰ;
46 ny → ɲ;
47 ph → pʰ;
48 qh → ǃʰ;
49 sh → ʃ;
50 th → tʰ;
51 tl → t\u0361ɬʼ;
52 ts → t\u0361sʼ;
53 ty → cʼ;
54 xh → ǁʰ;
55 aa → | a;
56 ee → | e;
57 ii → | i;
58 kc → | c;
59 kq → | q;
60 mm → | m;
61 oo → | o;
62 rh → | r;
63 uu → | u;
64 a → a;
65 b → ɓ;
66 c → ǀ;
67 d → d;
68 e → ɛ;
69 f → f;
70 g → ɡ;
71 h → h;
72 i → i;
73 j → d\u0361ʒ;
74 k → kʼ;
75 l → l;
76 m → m;
77 n } g → ŋ;
78 n → n;
79 o → ɔ;
80 p → pʼ;
81 q → ǃ;
82 r → r;
83 s → s;
84 t → tʼ;
85 u → u;
86 v → v;
87 w → w;
88 x → ǁ;
89 y → j;
90 z → z;
91