Back to Silas S. Brown's home page

lexconvert: a converter for phoneme codes and lexicon formats

As a person with limited vision, I often use speech synthesis software to read things.  Some uncommon words (such as names and places in literature) are pronounced wrongly by speech synthesizers, but if the synthesizer has a user-controlled pronunciation dictionary (lexicon) then this can be used to correct its pronunciation where necessary.  However, if you move to a different speech synthesizer, you may find the lexicon format is different.

To help, here is a Python program that converts between different codes for English phonemes and between lexicon files.  It supports quite a few, and there is information in the Python file about how to add your own.

Download lexconvert.py; usage information is below.

lexconvert v0.206 - convert phonemes between different speech synthesizers etc
(c) 2007-2012,2014 Silas S. Brown. License: GPL

Available pronunciation formats:

acapela-ukAcapela-optimised X-SAMPA for UK English voices (e.g. "Peter"), contributed by Jan Weiss
amigaAmigaOS speech synthesizer (American English)
android-picoX-SAMPA phonemes for the default "Pico" voice in Android (1.6+, American), wrapped in Java code
apolloDolphin Apollo 2 serial-port and parallel-port hardware synthesizers (in case anybody still uses those)
audapterAudapter Speech System, an old hardware serial/parallel-port synthesizer (American English)
bbcmicroBBC Micro Speech program from 1985 (see comments in lexconvert.py for more details)
braille-ipaIPA symbols in Braille (2008 BANA standard). By default Braille ASCII is output; if you prefer to see the Braille dots via Unicode, set the BRAILLE_UNICODE environment variable.
cepstralCepstral's British English SSML phoneset
cmuformat of the US-English Carnegie Mellon University Pronouncing Dictionary (contributed by Jan Weiss)
dectalkDECtalk hardware synthesizers (American English)
doubletalkDoubleTalk PC/LT serial-port hardware synthesizers (American English; assumes DOS driver by default, otherwise set DTALK_COMMAND_CODE to your current command-code binary value, e.g. export DTALK_COMMAND_CODE=1)
espeakeSpeak's default British voice
exampleA small built-in example lexicon for testing when you don't have your full custom lexicon to hand. Use --convert to write it in one of the other formats and see if a synth can import it.
festivalFestival's British voice
kana-approxRough approximation using kana (for getting Japanese computer voices to speak some English words - works with some words better than others). Set KANA_TYPE environment variable to hiragana or katakana (which can affect the sounds of some voices); default is hiragana
keynotePhoneme-read and lexicon-add codes for Keynote Gold hardware synthesizers (American English)
latex-ipaIPA symbols for typesetting in LaTeX using the "tipa" package
macapproximation in American English using the [[inpt PHON]] notation of Apple's US voices
mac-ukScansoft/Nuance British voices for Mac OS 10.7+ (system lexicon editing required, see --mac-uk option)
namesLexconvert internal phoneme names (sometimes useful with the --phones option while developing new formats)
pinyin-approxRough approximation using roughly the spelling rules of Chinese Pinyin (for getting Chinese-only voices to speak some English words - works with some words better than others)
rsynthrsynth text-to-speech C library (American English)
samSoftware Automatic Mouth (1982 American English synth that ran on C64, Atari 400/800/etc and Apple II/etc)
sapiMicrosoft Speech API (American English)
speakjetAllophone codes for the American English "SpeakJet" speech synthesis chip (the conversion from phonemes to allophones might need tweaking). Set the SPEAKJET_SYM environment variable to use mnemonics, otherwise numbers are used (set SPEAKJET_BINARY for binary output).
unicode-ipaIPA symbols in Unicode, as used by an increasing number of dictionary programs, websites etc
unicode-roughA non-standard notation that's reminiscent of unicode-ipa but changed so that more of the characters show in old browsers with incomplete fonts
x-sampaGeneral X-SAMPA notation (contributed by Jan Weiss)

Program options:

--convert <from-format> <to-format>
Convert a user lexicon (generally from its default filename; if this cannot be found then lexconvert will tell you what it should be).
E.g.: python lexconvert.py --convert festival cepstral
--phones <format> [<words>]
Use eSpeak to convert text to phonemes, and then convert the phonemes to format 'format'.
E.g.: python lexconvert.py --phones unicode-ipa This is a test sentence.
(Some commercial speech synthesizers do not work well when driven entirely from phonemes, because their internal format is different and is optimised for normal text.)
Set format to 'all' if you want to see the phonemes in ALL supported formats.
--phones2phones <format1> <format2> [<phonemes in format1>]
Perform a one-off conversion of phonemes from format1 to format2 (format2 can be 'all' if you want)
--try <format> [<pronunciation>]
Convert input from <format> into eSpeak and try it out.
(Requires the 'espeak' command.)
E.g.: python lexconvert.py --try festival h @0 l ou1
or: python lexconvert.py --try unicode-ipa '\u02c8\u0279\u026adn\u0329' (for Unicode put '\uNNNN' or UTF-8)
--trymac <format> [<pronunciation>]
Convert phonemes from <format> into Mac and try it using the Mac OS 'say' command
--trymac-uk <format> [<pronunciation>]
Convert phonemes from <format> and try it with Mac OS British voices (see --mac-uk for details)
--festival-dictionary-to-espeak <location>
Convert the Festival Oxford Advanced Learners Dictionary (OALD) pronunciation lexicon to eSpeak.
You need to specify the location of the OALD file in <location>,
e.g. for Debian festlex-oald package: python lexconvert.py --festival-dictionary-to-espeak /usr/share/festival/dicts/oald/all.scm
or if you can't install the Debian package, try downloading http://ftp.debian.org/debian/pool/non-free/f/festlex-oald/festlex-oald_1.4.0.orig.tar.gz, unpack it into /tmp, and do: python lexconvert.py --festival-dictionary-to-espeak /tmp/festival/lib/dicts/oald/oald-0.4.out
In all cases you need to cd to the eSpeak source directory before running this. en_extra will be overwritten. Converter will also read your ~/.festivalrc if it exists. (You can later incrementally update from ~/.festivalrc using the --convert option; the entries from the system dictionary will not be overwritten in this case.) Specify --without-check to bypass checking the existing eSpeak pronunciation for OALD entries (much faster, but makes a larger file and in some cases compromises the pronunciation quality).
--mac-uk <from-format> [<text>]
Speak text in Mac OS 10.7+ British voices while using a lexicon converted in from <from-format>. As these voices do not have user-modifiable lexicons, lexconvert must binary-patch your system's master lexicon; this is at your own risk! (Superuser privileges are needed the first time. A backup of the system file is made, and all changes are restored on normal exit but if you force-quit then you might need to restore the backup manually. Text speaking needs to be under lexconvert's control because it usually has to change the input words to make them fit the available space in the binary lexicon.) By default the Daniel voice is used; Emily or Serena can be selected by setting the MACUK_VOICE environment variable.
--syllables [<words>]
Attempt to break 'words' into syllables for music lyrics (uses espeak to determine how many syllables are needed)

All material © Silas S. Brown unless otherwise stated.