Eloquens™ is a text-to-speech software, whose first version was released in 1993 by CSELT. It was the first commercial speech synthesis software able to speak Italian.

Eloquens
Developer(s)CSELT
Initial release1993
Operating systemWindows
Available inItalian
TypeText to speech
LicenseProprietary Freeware

Description

edit

It was the first commercial product of the research center CSELT in the field of voice technology. It was built with diphone-technology aimed to reach a high computational efficiency.[1] As a result, the produced voice is still "robotic", but more natural than the previous generation voice implemented in MUSA[2] by CSELT itself. In the past, ELOQUENS was applied to automatically read timetables in the Italian train stations[3] and some telephone services provided by Telecom Italia, e.g. the automated address book service.[4]

In 1997 Eloquens was also used as a building block (synthezer module) in dialogue systems.[5]

Nowadays, it is released as freeware: it is nowadays typically used in spoken comments in many YouTube videos.

See also

edit

References

edit
  1. ^ Balestri, Marcello; Lazzaretto, Stefano; Salza, Pier Luigi; Sandri, Stefano (22 September 1993). "The CSELT system for Italian text-to-speech synthesis". 3rd European Conference on Speech Communication and Technology (Eurospeech 1993). pp. 2091–2094. doi:10.21437/Eurospeech.1993-468. S2CID 42744136.
  2. ^ Baggia, Paolo (7 June 2006). "Speech Technologies and Standards, DIT Seminars, Povo, Trento" (PDF).
  3. ^ 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing: April 21-24, 1997, Munich, Germany. (1997). United States: IEEE Computer Society Press: p. 1147
  4. ^ Nebbia, L.; Quazza, S.; Luigi Salza, P. (1998). "A specialised speech synthesis technique for application to automatic reverse directory service". Proceedings 1998 IEEE 4th Workshop Interactive Voice Technology for Telecommunications Applications. IVTTA '98 (Cat. No.98TH8376). pp. 223–228. doi:10.1109/IVTTA.1998.727725. ISBN 0-7803-5028-6. S2CID 62411997.
  5. ^ Gemello, R.; Albesano, D.; Mana, F. (1997). "Continuous speech recognition with neural networks and stationary-transitional acoustic units". Proceedings of International Conference on Neural Networks (ICNN'97). Vol. 4. pp. 2107–2111. doi:10.1109/ICNN.1997.614230. ISBN 0-7803-4122-8. S2CID 56858298.

Bibliography

edit
  • Billi, Roberto; Canavesio, Franco; Ciaramella, Alberto; Nebbia, L. (November 1995). "Interactive voice technology at work: The CSELT experience". Speech Communication. 17 (3–4): 263–271. doi:10.1016/0167-6393(95)00030-R.
  • Balestri, Marcello; Lazzaretto, Stefano; Salza, Pier Luigi; Sandri, Stefano (22 September 1993). "The CSELT system for Italian text-to-speech synthesis". 3rd European Conference on Speech Communication and Technology (Eurospeech 1993). pp. 2091–2094. doi:10.21437/Eurospeech.1993-468. S2CID 42744136.
  • Nebbia, L.; Quazza, S.; Luigi Salza, P. (1998). "A specialised speech synthesis technique for application to automatic reverse directory service". Proceedings 1998 IEEE 4th Workshop Interactive Voice Technology for Telecommunications Applications. IVTTA '98 (Cat. No.98TH8376). pp. 223–228. doi:10.1109/IVTTA.1998.727725. ISBN 0-7803-5028-6. S2CID 62411997.
  • Baggia, Paolo; Castagneri, Giuseppe; Danieli, Morena (August 2000). "Field trials of the Italian Arise train timetable system". Speech Communication. 31 (4): 355–367. doi:10.1016/S0167-6393(99)00068-0.
edit