kaa: Add initial support for Karakalpak language

Makefile.am

@@ -493,6 +493,7 @@ dictionaries: \
 	espeak-ng-data/ja_dict \
 	espeak-ng-data/jbo_dict \
 	espeak-ng-data/ka_dict \
+	espeak-ng-data/kaa_dict \
 	espeak-ng-data/kk_dict \
 	espeak-ng-data/kl_dict \
 	espeak-ng-data/kn_dict \
@@ -721,6 +722,9 @@ espeak-ng-data/jbo_dict: dictsource/jbo_list dictsource/jbo_rules dictsource/jbo
 ka: espeak-ng-data/ka_dict
 espeak-ng-data/ka_dict: dictsource/ka_list dictsource/ka_rules dictsource/ka_extra dictsource/ka_emoji
 
+kaa: espeak-ng-data/kaa_dict
+espeak-ng-data/kaa_dict: dictsource/kaa_list dictsource/kaa_rules dictsource/kaa_extra dictsource/kaa_emoji
+
 kk: espeak-ng-data/kk_dict
 espeak-ng-data/kk_dict: dictsource/kk_list dictsource/kk_rules dictsource/kk_extra dictsource/kk_emoji
 

dictsource/kaa_list

@@ -0,0 +1,34 @@
+// This file is UTF8 encoded
+// Spelling to phoneme rules for Karakalpak
+
+// Letters
+
+
+// Numbers
+_0 n'Yl
+_1 b'Ir
+_2 j'ekI
+_3 u#S
+_4 t8rt
+_5 b'es
+_6 'Alt@
+_7 Z'etI
+_8 s'egIz
+_9 t'oG@z
+_1X 'on
+_2X Z@g@rm'A
+_3X 'ot@z
+_4X q'@r@q
+_5X 'eliw
+_6X 'ALp@s
+_7X Zetp'Is
+_8X seks'en
+_9X toqs'An
+_0C Z'u#z
+_0M1 m'@N
+_0M2 m@jLL@j'on
+_1M2 m@jLL@j'on
+_0M3 m@jLL@j'Ard
+_1M3 m@jLL@j'Ard
+
+_dpt _Z&n'e_

dictsource/kaa_rules

@@ -0,0 +1,150 @@
+// This file is UTF8 encoded
+// Spelling to phoneme rules for Karakalpak language
+
+.replace
+// Replace Cyrillic script to Latin script
+    а    a
+    ә    á
+    б    b
+    в    v
+    г    g
+    ғ    ǵ
+    д    d
+    е    e
+    ё    yo
+    ж    j
+    з    z
+    и    i
+    й    y
+    к    k
+    қ    q
+    л    l
+    м    m
+    н    n
+    ң    ń
+    о    o
+    ө    ó
+    п    p
+    р    r
+    с    s
+    т    t
+    у    u
+    ү    ú
+    ў    w
+    ф    f
+    х    x
+    ҳ    h
+    ц    c
+    ч    ch
+    ш    sh
+    щ    sch
+    ы    ı
+    ь    ʼ
+    ъ    ʼ
+    э    e
+    ю    yu
+    я    ya
+
+.group a
+    a    A
+
+.group á
+    á    &
+
+.group b
+    b    b
+
+.group v
+    v    v
+
+.group g
+    g    g
+
+.group ǵ
+    ǵ    G
+
+.group d
+    d    d
+
+.group e
+    e    e
+
+.group j
+    j    Z
+
+.group z
+    z    z
+
+.group i
+    i    I
+
+.group y
+    y    j
+
+.group k
+    k    k
+
+.group q
+    q    q
+
+.group l
+    l    l
+
+.group m
+    m    m
+
+.group n
+    n    n
+
+.group ń
+    ń    N
+
+.group o
+    o    o
+
+.group ó
+    ó    8
+
+.group p
+    p    p
+
+.group r
+    r    *
+
+.group s
+    s    s
+    sch  SS
+    sh   S
+
+.group t
+    t    t
+
+.group u
+    u    U
+
+.group ú
+    ú    u#
+
+.group w
+    w    w
+
+.group f
+    f    f
+
+.group x
+    x    x
+
+.group h
+    h    h
+
+.group c
+    c    ts
+    ch   tS
+
+.group ı
+    ı    @
+
+.group
+    ʻ     ?
+    ş     S
+    ç     tS

espeak-ng-data/lang/trk/kaa

@@ -0,0 +1,2 @@
+name Karakalpak
+language kaa

phsource/ph_karakalpak

@@ -0,0 +1,137 @@
+
+// use "flag1" for soft vowels
+
+// short vowels
+
+phoneme I
+  vwl starttype #@ endtype #@
+  flag1
+  length 100
+  IF thisPh(isWordEnd) THEN
+    length 140
+  ENDIF
+  FMT(vowel/ii#)
+endphoneme
+
+phoneme 8
+  vwl starttype #@ endtype #@
+  length 100
+  IF thisPh(isWordEnd) THEN
+    length 140
+  ENDIF
+  FMT(vowel/8)
+endphoneme
+
+phoneme u#
+  vwl starttype @ endtype @
+  length 100
+  flag1
+  IF thisPh(isWordEnd) THEN
+    length 140
+  ENDIF
+  FMT(vdiph2/uw_6)
+endphoneme
+
+phoneme U
+  vwl starttype #u endtype #u
+  length 100
+  IF thisPh(isWordEnd) THEN
+    length 140
+  ENDIF
+  FMT(vowel/uu_2)
+endphoneme
+
+
+// long vowels
+
+phoneme A
+  vwl starttype #a endtype #a
+  length 200
+  FMT(vowel/aa_9)
+endphoneme
+
+phoneme a
+  vwl starttype #a endtype #a
+  length 200
+  FMT(vowel/a_5)
+endphoneme
+
+phoneme &
+  vwl starttype #a endtype #a
+  flag1
+  length 200
+  FMT(vowel/ee_2)
+endphoneme
+
+phoneme e
+  vwl starttype #e endtype #e
+  length 200
+  flag1
+  FMT(vdiph2/ii@_2)
+endphoneme
+
+phoneme E
+  vwl starttype @ endtype @
+  length 200
+  FMT(vowel/@_fnt)
+endphoneme
+
+phoneme i
+  vwl starttype #i endtype #i
+  length 180
+  FMT(vowel/ii_8)
+endphoneme
+
+phoneme o
+  vwl starttype #o endtype #o
+  length 200
+  FMT(vowel/o_3)
+endphoneme
+
+phoneme Y
+  vwl starttype #@ endtype #@
+  length 200
+  flag1
+  FMT(vowel/y#_4)
+endphoneme
+
+phoneme u
+  vwl starttype #u endtype #u
+  length 200
+  FMT(vowel/u_bck3)
+endphoneme
+
+phoneme r
+  import_phoneme base1/R2
+endphoneme
+
+phoneme t
+  import_phoneme base2/t
+endphoneme
+
+phoneme G
+  import_phoneme base1/r"
+endphoneme
+
+phoneme X
+  vls uvl frc
+  lengthmod 3
+  Vowelin f1=0  f2=2300 200 400  f3=-100 100
+  Vowelout f1=0 f2=2300 300 400  f3=-100 100  rms=20
+  lengthmod 3
+  WAV(ufric/x2, 60)
+endphoneme
+
+phoneme L
+  import_phoneme sq/ll
+//  import_phoneme base1/l-
+endphoneme
+
+phoneme l
+  liquid
+  IF nextPhW(isFlag1) THEN
+  ELSE
+    ChangePhoneme(L)  // Hard
+  ENDIF
+  CALL base1/l
+endphoneme

phsource/phonemes

@@ -2055,3 +2055,6 @@ phonemetable qdb en
 include ph_langbelta
 
 phonemetable ms id
+
+phonemetable kaa kk
+include ph_karakalpak

tests/language-phonemes.test

@@ -78,6 +78,7 @@ test_phwav it e2a438778434f699d9be469c4f9ea1576ec4fd03 "ma na n^a pa ba ta da ka
 test_phwav ja 6d1483048991b0205b9bc82cec24340a2184c42f "ma na n^a Na N\\a pa ba ta da ka ga t_sa d_za t_s\\a d_z\\a p\\a sa za s\\a z\\a Ca ha r\`a ja wa _:_ mi mu me mo ma mi~ mu~"
 test_phwav jbo 1bf9cf5c4898a24d2f71eae6f8a3e260895da884 "ma na Na pa ba ta da ka ga ?a fa va xa ha tSa dZa sa za Sa Za wa ja la Ra n-a r-a l-a _:_ ma me mi mo mu m@ maI maU meI moI"
 test_phwav ka 74a6f31909bdc9470e203a658614b6d2c961d7c3 "ma na p#a pa ba t#a ta da k#a ka ga qa ?a ts#a tsa tSa dza dZa va sa za Sa Za ca xa qa Qa ha ra la _:_ ma me mi mo mu m@ mo:"
+test_phwav kaa 2fffd426cd03d47f55829ebdd539a9a2f7b3dbd0 "ma na pa ba ta da tSa dZa tsa dza ca Ja Ca ka ga fa va sa za Sa Za xa Qa ha la ja wa Ra *a _:_ mi me m& my mW mu mo ma m@"
 test_phwav kk bb05c59779660929d7f0a7213189d89fcfc71675 "ma na pa ba ta da tSa dZa tsa dza ca Ja Ca ka ga fa va sa za Sa Za xa Qa ha la ja wa Ra *a _:_ mi me m& my mW mu mo ma m@"
 test_phwav kl 9b97b1ba5f35bb41a4be67e0a329cff9f494b2b1 "ma na Na pa ta ka qa tsa va sa Sa Qa ra la l#a ja tl#a _:_ ma me mi my mo mu m& mE mV mO mW m3 m@ maI"
 test_phwav kn 7a4943a8f06a29a5e59892edb6a39be91b20c2c2 "ma na n.a n^a Na pa p#a ba b#a ta t#a da d#a t.a t.#a d.a d.#a ka k#a ga g#a fa va sa S;a s.a ca c#a Ja J#a ha ja ra la l.a r-a _:_ ma ma: mi mi: mu mu: me me: mo mo: maI"