Date: Fri, 26 Jun 2015 20:29:20 -0700 (PDT)
From: sorpa'as plat <sorpaas@gmail.com>
To: lojban@googlegroups.com
Message-Id: <cc8533d8-082e-41e4-90b7-2987d1cdbe85@googlegroups.com>
Subject: [lojban] The Prototype of a Lojban Speech Recognition Tool
MIME-Version: 1.0
Content-Type: multipart/mixed; 
	boundary="----=_Part_2619_1607334825.1435375760016"
Reply-To: lojban@googlegroups.com
Precedence: list
Mailing-list: list lojban@googlegroups.com; contact lojban+owners@googlegroups.com
Sender: lojban@googlegroups.com
X-Spam_score: -2.0
X-Spam_score_int: -19
X-Spam_bar: --

------=_Part_2619_1607334825.1435375760016
Content-Type: multipart/alternative; 
	boundary="----=_Part_2620_1279608162.1435375760016"

------=_Part_2620_1279608162.1435375760016
Content-Type: text/plain; charset=UTF-8

Hi all,

I'm trying to build a Lojban speech recognition called tersku. Instead of 
building an acoustic model by hand (which may need many manpower and takes 
a long time), the attempt is to take the English acoustic model (which is 
pretty mature) and adapt it for Lojban sounds.

A running prototype can be found at https://git.null.tl/tersku.git (use 
*git://git.null.tl/tersku.git* to clone). The prototype uses a unmodified 
version of CMU's generic English acoustic model, with only necessary 
dictionary and grammars to parse the text "le tanxe be le birka cu cpana le 
tanxe be le botpi". To use it, recording a version of the text "le tanxe be 
le birka cu cpana le tanxe be le botpi", convert the recording to wav 
format, and replace the /resources/org/lojban/tersku/recording.wav file 
with it. The program will output the best "hypothesis" for the text.

The program does not work really well. That means there's lots of work and 
I would appreciate your help. Below are some details of things to be done.

*About the Program*
tersku uses CMU's Sphinx speech recognition engine. You can find Sphinx's 
tutorials and documentations at http://cmusphinx.sourceforge.net.

*Adapt the Acoustic Model*
The adaptation requires some 16KHZ single-channel wav recordings. Help are 
appreciated if someone can create a Lojban phrase recording collection. 
Note that a phrase recording collection will benefit the whole Lojban 
community but not just the speech recognition program :)

*Finish the Dictionary*
The dictionary in the prototype locates at 
resources/org/lojban/tersku/jbo-1.dict. Because we are trying to adapt the 
English acoustic model, all the phones are represented in Arpabet (
*https://en.wikipedia.org/wiki/Arpabet*). We will need to a) confirm which 
arpabet symbol represents which Lojban sound, and b) write a program that 
generates all the words in "[lojban word] [arpabet symbols]". This is 
probably dependent of the adaptation of the acoustic model.

*Finish the Grammar*
The grammar needs to be written in JSGF format (
http://cmusphinx.sourceforge.net/wiki/tutoriallm). This haven't been 
started yet (which needs help!).

*Correct Me!*
There must be mistakes and errors both in the codes and in the recognition 
details (I'm new to speech recognition!).

Feel free to reach me at this email address or by opening an task at 
https://phabricator.null.tl. I'm really looking forward to a Lojban speech 
recognition tool, because it should be one of the features of Lojban :)

Wei
mu'o mi'e la sorpa'as

-- 
You received this message because you are subscribed to the Google Groups "lojban" group.
To unsubscribe from this group and stop receiving emails from it, send an email to lojban+unsubscribe@googlegroups.com.
To post to this group, send email to lojban@googlegroups.com.
Visit this group at http://groups.google.com/group/lojban.
For more options, visit https://groups.google.com/d/optout.

------=_Part_2620_1279608162.1435375760016
Content-Type: text/html; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr">Hi all,<br><br>I'm trying to build a Lojban speech recogni=
tion called tersku. Instead of building an acoustic model by hand (which ma=
y need many manpower and takes a long time), the attempt is to take the Eng=
lish acoustic model (which is pretty mature) and adapt it for Lojban sounds=
.<br><br>A running prototype can be found at <a href=3D"https://git.null.tl=
/tersku.git">https://git.null.tl/tersku.git</a> (use <b>git://git.null.tl/t=
ersku.git</b> to clone). The prototype uses a unmodified version of CMU's g=
eneric English acoustic model, with only necessary dictionary and grammars =
to parse the text "le tanxe be le birka cu cpana le tanxe be le botpi". To =
use it, recording a version of the text "le tanxe be le birka cu cpana le t=
anxe be le botpi", convert the recording to wav format, and replace the /re=
sources/org/lojban/tersku/recording.wav file with it. The program will outp=
ut the best "hypothesis" for the text.<br><br>The program does not work rea=
lly well. That means there's lots of work and I would appreciate your help.=
 Below are some details of things to be done.<br><br><b>About the Program</=
b><br>tersku uses CMU's Sphinx speech recognition engine. You can find Sphi=
nx's tutorials and documentations at <a href=3D"http://cmusphinx.sourceforg=
e.net">http://cmusphinx.sourceforge.net</a>.<br><br><b>Adapt the Acoustic M=
odel</b><br>The adaptation requires some 16KHZ single-channel wav recording=
s. Help are appreciated if someone can create a Lojban phrase recording col=
lection. Note that a phrase recording collection will benefit the whole Loj=
ban community but not just the speech recognition program :)<br><br><b>Fini=
sh the Dictionary</b><br>The dictionary in the prototype locates at resourc=
es/org/lojban/tersku/jbo-1.dict. Because we are trying to adapt the English=
 acoustic model, all the phones are represented in Arpabet (<b>https://en.w=
ikipedia.org/wiki/Arpabet</b>). We will need to a) confirm which arpabet sy=
mbol represents which Lojban sound, and b) write a program that generates a=
ll the words in "[lojban word] [arpabet symbols]". This is probably depende=
nt of the adaptation of the acoustic model.<br><br><b>Finish the Grammar</b=
><br>The grammar needs to be written in JSGF format (<a href=3D"http://cmus=
phinx.sourceforge.net/wiki/tutoriallm">http://cmusphinx.sourceforge.net/wik=
i/tutoriallm</a>). This haven't been started yet (which needs help!).<br><b=
r><b>Correct Me!</b><br>There must be mistakes and errors both in the codes=
 and in the recognition details (I'm new to speech recognition!).<br><br>Fe=
el free to reach me at this email address or by opening an task at <a href=
=3D"https://phabricator.null.tl">https://phabricator.null.tl</a>. I'm reall=
y looking forward to a Lojban speech recognition tool, because it should be=
 one of the features of Lojban :)<br><br>Wei<br>mu'o mi'e la sorpa'as<br></=
div>

<p></p>

-- <br />
You received this message because you are subscribed to the Google Groups &=
quot;lojban&quot; group.<br />
To unsubscribe from this group and stop receiving emails from it, send an e=
mail to <a href=3D"mailto:lojban+unsubscribe@googlegroups.com">lojban+unsub=
scribe@googlegroups.com</a>.<br />
To post to this group, send email to <a href=3D"mailto:lojban@googlegroups.=
com">lojban@googlegroups.com</a>.<br />
Visit this group at <a href=3D"http://groups.google.com/group/lojban">http:=
//groups.google.com/group/lojban</a>.<br />
For more options, visit <a href=3D"https://groups.google.com/d/optout">http=
s://groups.google.com/d/optout</a>.<br />

------=_Part_2620_1279608162.1435375760016--
------=_Part_2619_1607334825.1435375760016--