Software:eSpeakNG

From HandWiki

eSpeakNG
Original author(s)Jonathan Duddington
Developer(s)Reece Dunn
Initial releaseFebruary 2006; 18 years ago (2006-02)
Stable release
1.49.2 / 24 September 2017; 6 years ago (2017-09-24)
Repositorygithub.com/espeak-ng/espeak-ng/
Written inC
Operating systemLinux
Windows
Mac OS X
FreeBSD
Size~1600 kbyte
TypeSpeech synthesizer
LicenseGNU GPL v3+
Websitegithub.com/espeak-ng/espeak-ng/

eSpeakNG is a compact, open source, software speech synthesizer for Linux, Windows, and other platforms. It uses a formant synthesis method, providing many languages in a small size. Much of the programming for eSpeakNG's language support is done using rule files with feedback from native speakers.

Because of its small size and many languages, it is included as the default speech synthesizer in the NVDA [1] open source screen reader for Windows, Android,[2] Ubuntu [3] and other Linux distributions. Its predecessor eSpeak was recommended by Microsoft in 2016[4] and was used by Google Translate for 27 languages in 2010;[5] 17 of these were subsequently replaced by commercial voices.[6]

The quality of the language voices varies greatly. In eSpeakNG's predecessor eSpeak, the initial version of each language was based on information found on Wikipedia.[7] Some languages have had more work or feedback from native speakers than others. Most of the people who have helped to improve the various languages are blind users of text-to-speech.

History

In 1995, Jonathan Duddington released the Speak speech synthesizer for RISC OS computers supporting British English.[8] On 17 February 2006, Speak 1.05 was released under the GPLv2 license, initially for Linux, with a Windows SAPI 5 version added in January 2007.[9] Development on Speak continued until version 1.14, when it was renamed to eSpeak.

Development of eSpeak continued from 1.16 (there was not a 1.15 release)[9] with the addition of an eSpeakEdit program for editing and building the eSpeak voice data. These were only available as separate source and binary downloads up to eSpeak 1.24. The 1.24.02 version of eSpeak was the first version of eSpeak to be version controlled using subversion,[10] with separate source and binary downloads made available on Sourceforge.[9] From eSpeak 1.27, eSpeak was updated to use the GPLv3 license.[11] The last official eSpeak release was 1.48.04 for Windows and Linux, 1.47.06 for RISC OS and 1.45.04 for Mac OS X.[12] The last development release of eSpeak was 1.48.15 on 16 April 2015.[13]

eSpeak NG

On 25 June 2010,[14] Reece Dunn started a fork of eSpeak on GitHub using the 1.43.46 release. This started off as an effort to make it easier to build eSpeak on Linux and other POSIX platforms.

On 4 October 2015 (6 months after the 1.48.15 release of eSpeak), this fork started diverging more significantly from the original eSpeak.[15][16]

On 8 December 2015, there were discussions on the eSpeak mailing list about the lack of activity from Jonathan Duddington over the previous 8 months from the last eSpeak development release. This evolved into discussions of continuing development of eSpeak in Jonathan's absence.[17][18] The result of this was the creation of the espeak-ng (Next Generation) fork, using the GitHub version of eSpeak as the basis for future development.

On 11 December 2015, the espeak-ng fork was started.[19] The first release of espeak-ng was 1.49.0 on 10 September 2016,[20] containing significant code cleanup, bug fixes, and language updates.

Features

eSpeakNG can be used as a command-line program, or as a shared library.

It supports Speech Synthesis Markup Language (SSML).

Language voices are identified by the language's ISO 639-1 code. They can be modified by "voice variants". These are text files which can change characteristics such as pitch range, add effects such as echo, whisper and croaky voice, or make systematic adjustments to formant frequencies to change the sound of the voice. For example, "af" is the Afrikaans voice. "af+f2" is the Afrikaans voice modified with the "f2" voice variant which changes the formants and the pitch range to give a female sound.

eSpeakNG uses an ASCII representation of phoneme names which is loosely based on the Kirshenbaum system.

Phonetic representations can be included within text input by including them within double square-brackets. For example:

espeak-ng -v en "Hello w3:ld"

will say About this soundHello world in English.

Synthesis method

File:ESpeakNG intro by eSpeakNG in English.ogg

eSpeakNG can be used as text-to-speech translator in different ways, depending on which text-to-speech translation step user want to use.

1. step — text to phoneme translation

There are many languages (notably English) which doesn't have straightforward one-to-one rules between writing and pronunciation. Therefore first step in text-to-speech generation have to be text-to-phoneme translation.

  1. input text is translated into pronunciation phonemes (e.g. input text xerox is translated into zi@r0ks for pronunciation).
  2. pronunciation phonemes are synthesized into sound e.g. zi@r0ks is voiced as About this soundzi@r0ks in monotone way

To add intonation for speech i.e. prosody data are necessary (e.g. stress of syllable, falling or rising pitch of basic frequency, pause, etc.) and other information, which allows to synthesize more human, non-monotonous speech. E.g. in eSpeakNG format stressed syllable is added using apostrophe: z'i@r0ks which provides more natural speech: About this soundz'i@r0ks with intonation

For comparison two samples with and without prosody data:

  1. DIs Iz m0noUntoUn spi:tS is spelled About this soundin monotone way
  2. DIs Iz 'Int@n,eItI2d sp'i:tS is spelled About this soundintonated way

If eSpeakNG is used for generation of prosody data only, then prosody data can be used as input for MBROLA diphone voices.

2. step — sound synthesis from prosody data

The eSpeakNG provides two different types of formant speech synthesis using its two different approaches. With its own eSpeakNG synthesizer and a Klatt synthesizer:[21]

  1. The eSpeakNG synthesizer creates voiced speech sounds such as vowels and sonorant consonants by additive synthesis adding together sine waves to make the total sound. Unvoiced consonants e.g. s are made by playing recorded sounds.,[22] because they are rich in harmonics, which makes additive synthesis less effective. Voiced consonants such as /z/ are made by mixing a synthesized voiced sound with a recorded sample of unvoiced sound.
  2. The Klatt synthesizer mostly uses the same formant data as the eSpeakNG synthesizer. But, it also produces sounds by subtractive synthesis by starting with generated noise, which is rich in harmonics, and then applying digital filters and enveloping to filter out necessary frequency spectrum and sound envelope for particular consonant (s, t, k) or sonorant (l, m, n) sound.

For the MBROLA voices, eSpeakNG converts the text to phonemes and associated pitch contours. It passes this to the MBROLA program using the PHO file format, capturing the audio created in output by MBROLA. That audio is then handled by eSpeakNG.

Languages

eSpeakNG performs text-to-speech synthesis for the following languages,:[23][24]



See also

References

  1. Switch to eSpeak NG in NVDA distribution #5651
  2. eSpeak TTS for Android
  3. espeak-ng package in Ubuntu
  4. https://support.office.com/en-us/article/download-voices-for-immersive-reader-read-mode-and-read-aloud-4c83a8d8-7486-42f7-8e46-2b0fdf753130
  5. Google blog, Giving a voice to more languages on Google Translate, May 2010
  6. Google blog, Listen to us now, December 2010.
  7. This is what Jonathan Duddington said on the mailing list.
  8. http://espeak.sourceforge.net/
  9. 9.0 9.1 9.2 https://sourceforge.net/projects/espeak/files/espeak/
  10. Subversion history (revision 1)
  11. Subversion history (revision 56)
  12. http://espeak.sourceforge.net/download.html
  13. http://espeak.sourceforge.net/test/latest.html
  14. https://github.com/rhdunn/espeak/commit/63daaecefccde34b700bd909d23c6dd2cac06e20
  15. https://github.com/rhdunn/espeak/commit/61522a12a38453a4e854fd9c9e0994ad80420243
  16. https://github.com/nvaccess/nvda/issues/5651#issuecomment-170288487
  17. Taking ownership of the eSpeak project and its future
  18. Vote for new main eSpeak developer
  19. Rebrand the espeak program to espeak-ng.
  20. espeak-ng 1.49.0
  21. Dennis H. Klatt (1979). "Software for a cascade/parallel formant synthesizer". J. Acoustical Society of America, 67(3) March 1980. http://www.fon.hum.uva.nl/david/ma_ssp/2010/Klatt-1980-JAS000971.pdf. 
  22. List of recorded fricatives in eSpeakNG
  23. https://github.com/espeak-ng/espeak-ng/blob/master/docs/languages.md
  24. https://github.com/espeak-ng/espeak-ng/blob/master/CHANGELOG.md
  25. 25.0 25.1 Butgereit, L., & Botha, A. (2009, May). Hadeda: The noisy way to practice spelling vocabulary using a cell phone. In The IST-Africa 2009 Conference, Kampala, Uganda.
  26. Hamiti, M., & Kastrati, R. (2014). Adapting eSpeak for converting text into speech in Albanian. International Journal of Computer Science Issues (IJCSI), 11(4), 21.
  27. 27.00 27.01 27.02 27.03 27.04 27.05 27.06 27.07 27.08 27.09 27.10 27.11 27.12 27.13 27.14 27.15 27.16 27.17 27.18 27.19 27.20 27.21 27.22 27.23 27.24 27.25 27.26 27.27 27.28 27.29 27.30 27.31 27.32 27.33 27.34 27.35 27.36 27.37 27.38 27.39 27.40 27.41 Kayte, S., & Gawali, D. B. (2015). Marathi Speech Synthesis: A review. International Journal on Recent and Innovation Trends in Computing and Communication, 3(6), 3708-3711.
  28. Pronk, R. (2013). Adding Japanese language synthesis support to the eSpeak system. University of Amsterdam.
  29. Mohanan, S., Salkar, S., Naik, G., Dessai, N. F., & Naik, S. (2012). Text Reader for Konkani Language. Automation and Autonomous System, 4(8), 409-414.
  30. Kaur, R., & Sharma, D. (2016). An Improved System for Converting Text into Speech for Punjabi Language using eSpeak. International Research Journal of Engineering and Technology, 3(4), 500-504.

External links