G - Physics – 10 – L
Patent
G - Physics
10
L
G10L 11/00 (2006.01) G10L 15/04 (2006.01) G10L 17/00 (2006.01) H04N 5/60 (2006.01) H04N 5/04 (2006.01)
Patent
CA 2448182
In one aspect, the invention divides an audio signal into auditory events, each of which tends to be perceived as separate and distinct, by calculating the spectral content of successive time blocks of the audio signal (5-1), calculating the difference in spectral content between successive time blocks of the audio signal (5-2), and identifying an auditory event boundary as the boundary between successive time blocks when the difference in the spectral content between such successive time blocks exceeds a threshold (5-3). In another aspect, the invention generates a reduced-information representation of an audio signal by dividing an audio signal into auditory events, each of which tends to be perceived as separate and distinct, and formatting and storing information relating to the auditory events (5-4). Optionally, the invention may also assign a characteristic to one or more of the auditory events (5-5).
Dans l'un de ses aspects, l'invention consiste à découper un signal audio en plusieurs événements auditifs, dont chacun tend à être perçu séparément et distinctement, par calcul du contenu spectral de blocs temporels successifs du signal audio (5-1), par calcul de la différence de contenu spectral existant entre les blocs temporels successifs du signal audio (5-2), et par identification d'une limite d'événement auditif constituant la limite entre les blocs temporels successifs lorsque la différence de contenu spectral entre ces blocs temporels successifs dépasse un seuil (5-3). Dans un autre de ses aspects, l'invention génère une représentation à informations limitées d'un signal audio par découpage de ce dernier en plusieurs événements auditifs, dont chacun tend à être perçu séparément et distinctement, puis par formatage et stockage des informations relatives aux événements auditifs (5-4). Eventuellement, l'invention peut également assigner une caractéristique à un ou plusieurs des événements auditifs (5-5).
Dolby Laboratories Licensing Corporation
Smart & Biggar
LandOfFree
Segmenting audio signals into auditory events does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Segmenting audio signals into auditory events, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Segmenting audio signals into auditory events will most certainly appreciate the feedback.
Profile ID: LFCA-PAI-O-1845434