addressalign-toparrow-leftarrow-rightbackbellblockcalendarcameraccwcheckchevron-downchevron-leftchevron-rightchevron-small-downchevron-small-leftchevron-small-rightchevron-small-upchevron-upcircle-with-checkcircle-with-crosscircle-with-pluscrossdots-three-verticaleditemptyheartexporteye-with-lineeyefacebookfolderfullheartglobegmailgooglegroupshelp-with-circleimageimagesinstagramFill 1linklocation-pinm-swarmSearchmailmessagesminusmoremuplabelShape 3 + Rectangle 1ShapeoutlookpersonJoin Group on CardStartprice-ribbonShapeShapeShapeShapeImported LayersImported LayersImported Layersshieldstartickettrashtriangle-downtriangle-uptwitteruserwarningyahoo

SF Bay ACM Chapter Message Board › New Meetup: Free ACM talk on Speech Recognition

New Meetup: Free ACM talk on Speech Recognition

Bill
Bill-ACM
Group Organizer
Mountain View, CA
Announcing a new Meetup for Meetup supporting SF Bay ACM Chapter!

What: Free ACM talk on Speech Recognition
When: Monday, July 25, 2011 6:30 PM

Where: LinkedIn
2025 Stierlin Ct
Mountain View, CA 94043

DMSIG – Segmental Conditional Random Fields in Speech Recognition Date Monday, July 25, 2011 - 6:30pm - 9:00pm Venue LinkedIn­ LinkedIn 2025 Stierlin Ct. Mountain View, CA 94043 See map: Google Maps Speaker: Patrick Nguyen Event Details

Novel techniques in speech recognition are often hampered by the long road that must be followed to turn them into fully functional systems capable of competing with the state-of-the-art. In this work, we explore the use of Segmental Conditional Random Fields as an integrating technology which can augment the best conventional systems with information from novel scientific approaches. Segmental Conditional Random Fields provide a principled, flexible framework to express a new class of claims that are either impossible or cumbersome to integrate in current speech recognition systems based on Hidden Markov Models. We illustrate the approach with work done at Microsoft and applied at a Johns Hopkins University workshop, in which we find that the SCRF framework is able to appropriately weight different information sources. Joint work with Geoff Zweig at Microsoft Research.

Speaker Bio

Patrick Nguyen is a research scientist in Google Research, Mountain View, CA. Prior to joining Google, he was with Microsoft Research in Redmond, WA from 2004-2010. Prior to that, he was working at the Panasonic Speech Technology Laboratory from 2000-2004, in Santa Barbara, CA. In 1998 he started a company which provided a market-maker platform for real-time foreign exchange trading. He received his Doctorate degree from the Swiss Federal Institute for Technology (EPFL) in 2002. His area of expertise revolves around statistical processing human language, and in particular speech recognition. He participated in NIST competitions, notably contributing to the winning machine translation competition in English to Chinese in 2008. He co-authored about 15 granted patents and numerous publications. He serves a reviewer for all major speech and natural language research publications. He serves in the organizing committee of ASRU 2011.



Check it out!
Powered by mvnForum

Our Sponsors

  • Association for Computing Machinery

    World’s largest educational and scientific computing society

  • UCSC Silicon Valley Extension

    Offers professional technology courses in Silicon Valley and online

  • eBay

    Data Science SIG Meeting Venue and Past Data Science Camp Sponsor

  • Intel

    Data Science Camp Venue Sponsor & Special Event Sponsor

  • Target Digital

    2016 General Meeting Venue Sponsor Target.com Research in Sunnyvale

  • Symantec

    2016 General Meeting Venue Sponsor

  • Pivotal

    2016 Data Science SIG Meeting Venue, Video, and Pizza Sponsor

  • PayPal

    Data Science Camp & Professional Development Seminar Venue Sponsor

  • HP

    Past General Meeting Sponsor

  • O'Reilly

    EBook, Book, Video & Conference Discounts and Donations

People in this
Meetup are also in:

Sign up

Meetup members, Log in

By clicking "Sign up" or "Sign up using Facebook", you confirm that you accept our Terms of Service & Privacy Policy