BROWSE TOPICS

RESOURCES

ABOUT THIS SITE

 

Speech Recognition Leaps Forward

Speech Recognition Leaps Forward During Interspeech 2011 , the 12th annual Conference of the International Speech Communication Association being held in Florence, Italy, from Aug. 28 to 31, researchers from Microsoft Research will present work that dramatically improves the potential of real-time, speaker-independent, automatic speech recognition. Dong Yu , researcher at Microsoft Research Redmond , and Frank Seide , senior researcher and research manager with Microsoft Research Asia , have been spearheading this work, and their teams have collaborated on what has developed into a research breakthrough in the use of artificial neural networks for large-vocabulary speech recognition. The notion of using ANNs to improve speech-recognition performance has been around since the 1980s, and a model known as the ANN-Hidden Markov Model (ANN-HMM) showed promise for large-vocabulary speech recognition. The new project applied CD-DNN-HMM models to speech-to-text transcription and was tested against Switchboard, a highly challenging phone-call transcription benchmark recognized by the speech-recognition research community.

Author: Publication Date: Crawl Date: Source: Topic: Contributor: Type: Language: Format:
August 29, 2011 September 04, 2011 All About Symbian via Google News Applications MachineLearning NaturalLanguage Speech Vision NewsFinder Text English HTML

Whitelist words:

  1. speech recognit: 27 occurrences
  2. neural network: 11 occurrences

Categorization (need >= 0.5 to match):

  1. AIOverview: 0.0124329
  2. Agents: 0.00977345
  3. Applications: 0.834133
  4. CognitiveScience: 0.00814002
  5. Education: 0.0148272
  6. Ethics: 0.0147587
  7. Games: 0.00902422
  8. History: 0.0184761
  9. Interfaces: 0.0733096
  10. MachineLearning: 0.849654
  11. NaturalLanguage: 0.986909
  12. Philosophy: 0.00297714
  13. Reasoning: 0.0141305
  14. Representation: 0.00620414
  15. Robots: 0.00105361
  16. ScienceFiction: 0.00145525
  17. Speech: 0.991375
  18. Systems: 0.0195927
  19. Vision: 0.605517

Duplicates (threshold=0.17):

  1. (sim=0.455) 2821: Speech recognition breakthrough

Transcript:

  1. Preferred over duplicates
  2. Published
Collections:
brokenlinkform:brokenlink
AAAI   Recent Changes   Edit   History   Print   Contact Us
Page last modified on September 04, 2011, at 08:02 PM