[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[lojban-beginners] espeak text to speech for lojban
- To: lojban-beginners@lojban.org, jonsd@users.sourceforge.net
- Subject: [lojban-beginners] espeak text to speech for lojban
- From: "Stephen Pollei" <stephen.pollei@gmail.com>
- Date: Mon, 25 Aug 2008 22:21:32 -0700
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:received:received:message-id:date:from:to :subject:mime-version:content-type:content-transfer-encoding :content-disposition; bh=KAFu7LVNaGQO6uQ7/TWfjgjUaGwhhk6Wa2OS+iWH4mM=; b=gvB84orDskAARSO8fGg3gMYIDencbTZpnFNx0qyWLa+H8oFk3vq91eOg687bWR8EzQ 833WH3f37HuJHUusP99wRXVHtObp7qVOLPNBZoVWMCCKA87UGw6FpGZGNqY6mDKciu4Q SV/8mtuC5OZ79LuPiy0AN0hx0yZBmfHqyWqHw=
- Domainkey-signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=message-id:date:from:to:subject:mime-version:content-type :content-transfer-encoding:content-disposition; b=CI8k5vqv5ymfARXawIZh9b0ylFWvKWP/c1W81I4acGeVJcOcvZnAiegPXKlueXV1Fz tUSbeSWHYtCL/ml/Vp3l61AtCExzP3/jSIHcwJRrC3KUj0O5v6n59J6WCwkFpONEBaYJ hQLGB7jeO7mrdVhh8krPR1FKtR5YlS+0z1+1U=
- Reply-to: lojban-beginners@lojban.org
- Sender: lojban-beginners-bounce@lojban.org
I looked into the report at
http://www.lojban.org/tiki/tiki-view_forum_thread.php?forumId=5&comments_parentId=6701
that espeak was mispronouncing certain letters. I downloaded
espeak-1.38-source and altered
espeak-1.38-source/dictsource/jbo_rules and
espeak-1.38-source/dictsource/jbo_list .
for jbo_list the fix was easy I simply deleted most of it.
_0 no
_1 pa
_2 Re
_3 Si
_4 vo
_5 mu
_6 xa
_7 ze
_8 bi
_9 so
_dpt pi
was all that was maybe needed. lojban should be a phometic language so
all the other things probably was just causing issues.
for jbo_rules I simply added pausing rules for things that begin with
vowels. dj and tc shouldn't need special rules . gi'V shouldn't need
extra help . l and r should need the extra stuff they have and n
doesn't change based on if g or k follows it. the pausing rules and
word boundary rules for lojban are probably complex enough that a
special front end should be created to split words and insert
mandatory pauses(".") were needed. Also stress in lojban is based on
brivla Vs cmavo Vs. cmene , and if a capital letter is put in there.
special front end should probably do stress markings as well.
Truth be told I didn't compile or test any of these changes and I
wanted opinion from some who are more knowlegdable than me to comment
and test.
--- jbo_rules.orig 2008-01-17 17:08:21.000000000 -0800
+++ jbo_rules 2008-08-25 22:12:55.000000000 -0700
@@ -9,8 +9,12 @@
ai aI
au aU
X) a (_ %a // single-syllable cmavo are unstressed
+ // probably needs better way to do stressed/unstressed
X) ai (_ %aI
X) au (_ %aU
+ _) a _a
+ _) ai _aI
+ _) au _aU
.group b
b b
@@ -20,13 +24,15 @@
.group d
d d
- dj dZ
+// dj dZ
.group e
e e
ei eI
X) e (_ %e
X) ei (_ %eI
+ _)e _e
+ _)ei _eI
.group f
f f
@@ -34,7 +40,7 @@
.group g
g g
- _) gi ('A_ _;_gi
+// _) gi ('A_ _;_gi
.group h
h h
@@ -44,6 +50,8 @@
i (A j
X) i (_ %i
X) i (A_ %j
+ _)i _i
+ _)i (A _j
.group j
j Z
@@ -55,20 +63,23 @@
l l-
A) l l
l (A l
+// not sure why this is stuff is here for l
.group m
m m
.group n
n n
- n (g N
- n (k N
+// n (g N
+// n (k N
.group o
o o
oi OI
X) o (_ %o
X) oi (_ %OI
+ _)o _o
+ _)oi _OI
.group p
p p
@@ -80,6 +91,7 @@
r r-
A) r R
r (A R
+// not sure what to do here
.group s
@@ -87,13 +99,15 @@
.group t
t t
- tc tS
+// tc tS
.group u
u u
u (A w
X) u (_ %u
X) u (A_ %w
+ _)u _u
+ _)u (A _w
.group v
v v
@@ -106,6 +120,7 @@
.group y
y @
+ _) y _@
.group z
z z