Difference between revisions of "Lojban Speech Synthesis"

From Lojban
Jump to navigation Jump to search
(creates the page)
 
m (source editing)
Tag: 2017 source edit
 
(One intermediate revision by the same user not shown)
Line 1: Line 1:
 +
== [https://github.com/DanRuta/xVA-Synth xVASynth] ==
 +
 +
While the Open Source project supports only English with upcoming [https://en.wikipedia.org/wiki/International_Phonetic_Alphabet IPA] support. A Lojban voice can be trained by replacing the [https://en.wikipedia.org/wiki/ARPABET ARPAbet] dictionary with Lojban equivalent pronunciations. The voice of [[User:Selpahi|la selpa'i]] was synthesized using [https://www.youtube.com/playlist?list=PLG78r1RXBYz0fPNhkqvb-cFZylPB4PSHa Lojban Corpus Readings] as audio sources. The English ARPABet dictionaries have to be disabled for it to work properly.
 +
 +
[[File:xvasynth selpahi example 1.wav|left|thumb]]
 +
 +
xVASynth voice model: https://drive.google.com/drive/u/0/folders/1Ipk5UvPgorvwnVEaI5Tb1Cc4CKn_raTm
 +
 +
Selpahi dataset: https://drive.google.com/drive/u/0/folders/1Ipk5UvPgorvwnVEaI5Tb1Cc4CKn_raTm
 +
 +
 
== eSpeak ==
 
== eSpeak ==
  

Latest revision as of 12:09, 17 July 2022

xVASynth

While the Open Source project supports only English with upcoming IPA support. A Lojban voice can be trained by replacing the ARPAbet dictionary with Lojban equivalent pronunciations. The voice of la selpa'i was synthesized using Lojban Corpus Readings as audio sources. The English ARPABet dictionaries have to be disabled for it to work properly.

File:xvasynth selpahi example 1.wav

xVASynth voice model: https://drive.google.com/drive/u/0/folders/1Ipk5UvPgorvwnVEaI5Tb1Cc4CKn_raTm

Selpahi dataset: https://drive.google.com/drive/u/0/folders/1Ipk5UvPgorvwnVEaI5Tb1Cc4CKn_raTm


eSpeak

The Open Source eSpeak supports Lojban.

Web Version

https://eeejay.github.io/espeak/emscripten/espeak.html

Select the "lojban (jbo)" voice.

Command Line Version

https://github.com/espeak-ng/espeak-ng

espeak-ng -v jbo

You can then type any Lojban text and press return for it to be read out-loud. Don't press any arrow keys when entering text, as that will cause problems - backspace works fine.

GUI Version

http://espeak.sourceforge.net/

Type in 'jbo' when installing the languages

Other software

http://members.home.nl/w.dijkhuis/lojban/z0300_txt2speech_01.htm has some more TTS examples.

There is also lojban_diphone_speech_synthesizer which uses Praat, but a lot of its links are dead now.