Bell Labs, the R&D division of Lucent Technologies, recently launched a multi-lingual interactive text-to-speech site, which enables users to produce what Lucent calls "natural speech" in German, French, Romanian, Mandarin and Taiwanese Chinese, Spanish (Peninsular and Mexican), Russian, English, and Italian, directly from written text.
"Speech is a sound signal used for language communication. Bell Labs researchers, world experts in signal processing, speech modeling, and text analysis, have devoted decades of work to improving the quality of synthetic speech," said Joe Olive, head of the Language Modeling Research Department at Bell Labs, in a press release. "The applications for text-to-speech synthesis are various, and growing, and they include e-mail readers, voice-response systems, and automatic order-verification systems," said Olive. "Such systems will require the high-quality word pronunciation and speech intelligibility that Bell Labs TTS systems deliver."
The Bell Labs TTS system converts written text to speech on-the-fly through sophisticated linguistic analysis, prosodic modeling, and speech synthesis. Phrases typed by a user on his or her PC are enriched by phrasing information, intonation, and stress, and then generated into clearly articulated speech.
More information about Bell Lab's TTS can be obtained at:
http://www.bell-labs.com/project/tts
Use the following reformatted form to submit English phrases, words, or sentences to be converted into speech:
If you had fun playing with the English TTS, you might want to check out the speech-friendly reformat of the Pig Latin "Translator", or any of the other demo pages at the TTS site:
Select this link to return to
Moving Targets
Select this link to return to VICUG NYC's front
page
Select this link to return to the top of this
page
This page was created on May 1, 1997
Last modified February 21, 1998