The combination of audio and video speech recognition in a manner to improve the robustness of speech recognition systems in noisy environments. Contemplated are methods and apparatus in which a video signal associated with a video source and an audio signal associated with the video signal are processed, the most likely viseme associated with the audio signal and video signal is determined and, thereafter, the most likely phoneme associated with the audio signal and video signal is determined.

A combinação do recognition de discurso audio e video em uma maneira para melhorar o robustness de sistemas do recognition de discurso em ambientes ruidosos. São contemplados os métodos e o instrumento em que um sinal video associou com uma fonte video e um sinal audio associado com o sinal video é processado, o viseme mais provável associado com o sinal audio e o sinal video são determinados e, depois disso, o fonema mais provável associado com o sinal audio e o sinal video é determinado.

 
Web www.patentalert.com

< Computer game

< Method for displaying toilet training materials and display kiosk using same

> System and method for adaptive knowledge access and presentation

> Concealment-type word puzzle/game

~ 00086