Abstract: The present disclosure relates to systems and methods that recognize audio queries and select related information to return in response to recognition of the audio queries. The technology disclosed facilitates easy designation of aggregate user experience categories and custom audio references to be recognized. It facilitates linking and return of selected information in response to recognition of audio queries that match the designated aggregate user experience categories or custom audio references to be recognized.
Abstract: The technology disclosed relates to a system and method for fast, accurate and parallelizable speech search, called Crystal Decoder. It is particularly useful for search applications, as opposed to dictation. It can achieve both speed and accuracy, without sacrificing one for the other. It can search different variations of records in a reference database without a significant increase in elapsed processing time. This is accomplished by first accessing the database, and for each word representation in the database, searching an utterance for likely instances of the word representation utilizing multiple parallel processors. Even the main decoding part can be parallelized as the number of words increase to maintain a fast response time.
Type:
Grant
Filed:
November 2, 2009
Date of Patent:
August 12, 2014
Assignee:
Soundbound, Inc.
Inventors:
Keyvan Mohajer, Seyed Majid Emami, Jon Grossman, Joe Kyaw Soe Aung, Sina Sohangir