International Business Machines Corporation

Edward J Gleason

Paul S Cohen

William J Ablondi

Paul S Roossin

John R Dildine

A system and method for eliminating synchronization errors using speech recognition. Using separate audio and visual speech recognition techniques, the inventive system and method identifies visemes, or visual cues which are indicative of articulatory type, in the video content, and identifies phones and their articulatory types in the audio content. Once the two recognition techniques have been applied, the outputs are compared to determine the relative alignment and, if not aligned, a synchronization algorithm is applied to time-adjust one or both of the audio and the visual streams in order to achieve synchronization.

System and method for eliminating synchronization errors in electronic audiovisual transmissions and presentations

A system and method for detecting the presence of a particular source of audible content using an automatic speech recognizer component which is trained to recognize specific non-speech sounds. Training of the automatic speech recognizer component is accomplished by providing an appropriate model to be recognized and by tuning the automatic speech recognizer to the sounds created by the desired stimulus. The automatic speech recognizer can additionally be provided with processing means for distinguishing the desired stimulus from an irrelevant or unwanted stimulus which may have acoustic signatures with a high degree of similarity to that of the desired stimulus. The invention can be implemented in a portable detector to allow detection of a specific acoustic source at any location.

Growing community of inventors

Yorktown Heights, NY, United States of America

Edward J Gleason