System and method for audio/video speaker detection

Details System and method for audio/video speaker detection System and method for audio/video speaker detection

2003-06-25

2008-03-11

Hudspeth, David (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Synthesis

Reexamination Certificate

active

07343289

ABSTRACT:
A system and method for detecting speech utilizing audio and video inputs. In one aspect, the invention collects audio data generated from a microphone device. In another aspect, the invention collects video data and processes the data to determine a mouth location for a given speaker. The audio and video are inputted into a time-delay neural network that processes the data to determine which target is speaking. The neural network processing is based upon a correlation to detected mouth movement from the video data and audio sounds detected by the microphone.

REFERENCES:
patent: 5539483 (1996-07-01), Nalwa
patent: 5586215 (1996-12-01), Stork et al.
patent: 5745305 (1998-04-01), Nalwa
patent: 5793527 (1998-08-01), Nalwa
patent: 5990934 (1999-11-01), Nalwa
patent: 6005611 (1999-12-01), Gullichsen et al.
patent: 6043837 (2000-03-01), Driscoll, Jr. et al.
patent: 6111702 (2000-08-01), Nalwa
patent: 6115176 (2000-09-01), Nalwa
patent: 6128143 (2000-10-01), Nalwa
patent: 6141145 (2000-10-01), Nalwa
patent: 6144501 (2000-11-01), Nalwa
patent: 6175454 (2001-01-01), Hoogland et al.
patent: 6195204 (2001-02-01), Nalwa
patent: 6219089 (2001-04-01), Driscoll, Jr. et al.
patent: 6219090 (2001-04-01), Nalwa
patent: 6219639 (2001-04-01), Bakis et al.
patent: 6219640 (2001-04-01), Basu et al.
patent: 6222683 (2001-04-01), Hoogland et al.
patent: 6285365 (2001-09-01), Nalwa
patent: 6313865 (2001-11-01), Driscoll, Jr. et al.
patent: 6331869 (2001-12-01), Furlan et al.
patent: 6337708 (2002-01-01), Furlan et al.
patent: 6341044 (2002-01-01), Driscoll, Jr. et al.
patent: 6346967 (2002-02-01), Gullichsen et al.
patent: 6356296 (2002-03-01), Driscoll, Jr. et al.
patent: 6356397 (2002-03-01), Nalwa
patent: 6369818 (2002-04-01), Hoffman et al.
patent: 6373642 (2002-04-01), Wallerstein et al.
patent: 6388820 (2002-05-01), Wallerstein et al.
patent: 6392687 (2002-05-01), Driscoll, Jr. et al.
patent: 6424377 (2002-07-01), Driscoll, Jr. et al.
patent: 6426774 (2002-07-01), Driscoll, Jr. et al.
patent: 6459451 (2002-10-01), Driscoll, Jr. et al.
patent: 6466254 (2002-10-01), Furlan et al.
patent: 6480229 (2002-11-01), Driscoll, Jr. et al.
patent: 6493032 (2002-12-01), Wallerstein et al.
patent: 6515696 (2003-02-01), Driscoll, Jr. et al.
patent: 6539547 (2003-03-01), Driscoll, Jr. et al.
patent: 6567775 (2003-05-01), Maali et al.
patent: 6583815 (2003-06-01), Driscoll, Jr. et al.
patent: 6593969 (2003-07-01), Driscoll, Jr. et al.
patent: 6597520 (2003-07-01), Wallerstein et al.
patent: 6700711 (2004-03-01), Nalwa
patent: 6707921 (2004-03-01), Moore
patent: 6735566 (2004-05-01), Brand
patent: 6741250 (2004-05-01), Furlan et al.
patent: 6756990 (2004-06-01), Koller
patent: 6885509 (2005-04-01), Wallerstein et al.
patent: 6924832 (2005-08-01), Shiffer et al.
patent: 7165029 (2007-01-01), Nefian
patent: 2002/0034020 (2002-03-01), Wallerstein et al.
patent: 2002/0063802 (2002-05-01), Gullichsen et al.
patent: 2002/0094132 (2002-07-01), Hoffman et al.
patent: 2002/0154417 (2002-10-01), Wallerstein et al.
patent: 2003/0142402 (2003-07-01), Carbo, Jr. et al.
patent: 2003/0193606 (2003-10-01), Driscoll, Jr. et al.
patent: 2003/0193607 (2003-10-01), Driscoll, Jr. et al.
patent: 2003/0212552 (2003-11-01), Liang et al.
patent: 2004/0008407 (2004-01-01), Wallerstein et al.
patent: 2004/0008423 (2004-01-01), Driscoll, Jr. et al.
patent: 2004/0021764 (2004-02-01), Driscoll, Jr. et al.
patent: 2004/0122675 (2004-06-01), Nefian et al.
patent: 2004/0252384 (2004-12-01), Wallerstein et al.
patent: 2004/0254982 (2004-12-01), Hoffman et al.
patent: 2004/0267521 (2004-12-01), Cutler et al.
Cutler, R. and Davis, L. “Look Who's Talking: Speaker Detection Using Video and Audio Correlation”.IEEE International Conference on Multimedia and Expo 2000, New York, New York. 2000.

Affiliated with

Also associated with

Rating

System and method for audio/video speaker detection does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with System and method for audio/video speaker detection, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for audio/video speaker detection will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3976271