Home | History | Annotate | Download | only in transforms 
      1 <?xml version="1.0" encoding="UTF-8" ?>
      2 <!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
      3 <!-- Copyright  1991-2015 Unicode, Inc.
      4 CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)
      5 For terms of use, see http://www.unicode.org/copyright.html -->
      6 <supplementalData>
      7 	<version number="$Revision: 12347 $" />
      8 	<transforms>
      9 		<transform source="xh" target="xh_FONIPA" direction="forward" alias="xh-fonipa-t-xh">
     10 			<tRule><![CDATA[
     11 # Pronunciation rules for isiXhosa.
     12 #
     13 # Author: mjansche (a] 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.  instead of , to
     30 # avoid ambiguity and make the phoneme inventory uniquely decodable.
     31 
     32 ::Lower;
     33 
     34 nyh  ;
     35 n { tsh  t;
     36     tsh  t;
     37 tyh  c;
     38 
     39 bh  b;
     40 ch  ;
     41 dl  ;
     42 dy  ;
     43 gc  ;
     44 gq  ;
     45 gr  ;
     46 gx  ;
     47 hl  ;
     48 kh  k;
     49 kr  kx;
     50 mh } [^l]  m;  # <mhl> denotes /m/ instead
     51 nh  n;
     52 ny  ;
     53 ph  p;
     54 qh  ;
     55 sh  ;
     56 th  t;
     57 tl  t;
     58 ts  ts;
     59 ty  c;
     60 xh  ;
     61 
     62 aa  | a;
     63 ee  | e;
     64 ii  | i;
     65 kc  | c;
     66 kq  | q;
     67 mm  | m;
     68 oo  | o;
     69 rh  | r;
     70 uu  | u;
     71 
     72 a  a;
     73 b  ;
     74 c  ;
     75 d  d;
     76 e  ;
     77 f  f;
     78 g  ;
     79 h  h;
     80 i  i;
     81 j  d;
     82 k  k;
     83 l  l;
     84 m  m;
     85 n } g  ;
     86 n  n;
     87 o  ;
     88 p  p;
     89 q  ;
     90 r  r;
     91 s  s;
     92 t  t;
     93 u  u;
     94 v  v;
     95 w  w;
     96 x  ;
     97 y  j;
     98 z  z;
     99 			]]></tRule>
    100 		</transform>
    101 	</transforms>
    102 </supplementalData>
    103