Alert icon
We're changing our privacy policy. This stuff matters.  Learn more  Dismiss

Speech Technologies and Platforms - Present and Future Evolutions

Loading...

Sign in or sign up now!
7,547
Loading...
Alert icon
Sign in or sign up now!
Alert icon

Uploaded by on Mar 8, 2008

Google Tech Talks
March 3, 2008

ABSTRACT

At the end of the last century, the landscape of speech applications was abruptly changed due to the convergence of several factors: the maturity of speech technologies and the advent of standards and platforms.

The talk will give a clear picture of the current status of technologies and platforms in use in today speech applications and highlights of the trends of evolution.

Slides for this talk are available here:
http://sites.google.com/site/paolobaggia/Home/BaggiaGoogleTechTalk.pdf?attred...

Speaker: Paolo Baggia, Director of International Standards, Loquendo
Paolo Baggia is currently Director of International Standards of Loquendo and actively involved in W3C and the VoiceXML Forum, where he is a member of the Board of Directors. Formerly, he lead the VoiceXML browser development for Loquendo's VoxNauta platform. In 1989, he joined CSELT, Telecom Italia's R lab, and was involved in several research activities, including natural language, speech parsing, spoken dialog design, and language modeling. In 1999, he took part in a large-scale speech application: the automation of TreniItalia railway company's call centers. He holds a degree in computer science from the Università di Torino.

Category:

Science & Technology

Tags:

License:

Standard YouTube License

  • likes, 4 dislikes

Link to this comment:

Share to:
see all

All Comments (7)

Sign In or Sign Up now to post a comment!
  • @MariaLoquendo baboso xD

  • Loquendo TTS es el mejor sintetizador de voz, es mas real !

  • My slides were attached to the abstract above, click on "more info"

  • Excellent presentation with very useful information. Could anybody please provide me a link where I can find the slides of the presentation.

  • I like the synthetic voice at 05:00.

  • My point was that the most recent TTS technique, called Concatenative Unit Selection, is much more natural then the previous ones. There is a big difference between this technique and the previous ones.

    It's much less robotic, almost natural.

    I'll point you the audio clip when I'll upload them somewhere.

    Regards,

    PaoloB (Pao662)

  • IT WILL ALWAYS SOUND ROBOTIC

Loading...

0 / 00Unsaved Playlist Return to active list
    1. Your queue is empty. Add videos to your queue using this button:
      or sign in to load a different list.
    Loading...Loading...Saving...
    • Clear all videos from this list
    • Learn more