Method and system for post-processing speech recognition results
Number of patents in Portfolio can not be more than 2000
United States of America Patent
Stats
-
Mar 25, 2014
Grant Date -
N/A
app pub date -
May 16, 2009
filing date -
May 21, 2008
priority date (Note) -
In Force
status (Latency Note)
Importance
Abstract
A system and a method to correct semantic interpretation recognition errors presented in this invention applies to Automatic Speech Recognition systems returning recognition results with semantic interpretations. The method finds the most likely intended semantic interpretation given the recognized sequence of words and the recognized semantic interpretation. The key point is the computation of the conditional probability of the recognized sequence of words given the recognized semantic interpretation and a particular intended semantic interpretation. It is done with the use of Conditional Language Models which are Statistical Language Models trained on a corpus of utterances collected under the condition of a particular recognized semantic interpretation and a particular intended semantic interpretation. Based on these conditional probabilities and the joint probabilities of the recognized and intended semantic interpretations, new semantic interpretation confidences are computed. The semantic interpretation with the maximum new confidence is declared the corrected semantic interpretation.
First Claim
Family
International Classification(s)
- [Classification Symbol]
- [Patents Count]
Cited Art Landscape
Patent Citation Ranking
Advertisement
Advertisement
Advertisement
Recipient Email Address
Recipient Email Address
Comment
Recipient Email Address
Add to Portfolio(s)
To add this patent to one, or more, of your portfolios, simply click the add button.
This Patent is in these Portfolios:
Add to additional portfolios:
Last Refreshed On:
Changes done successfully