US 12,334,047 B1
System and method for automatically editing voice signals
Mark Paxman Warnick, San Antonio, TX (US); Nathan Lee Post, Rockport, TX (US); Joel S. Hartshorn, Port Orchard, WA (US); Christian A. Williams, San Antonio, TX (US); Will Kerns Maney, Jr., New York City, NY (US); Ravi Durairaj, San Antonio, TX (US); Nolan Serrao, Plano, TX (US); and Donald Nathaniel Holloway, III, San Antonio, TX (US)
Assigned to United Services Automobile Association (USAA), San Antonio, TX (US)
Filed by UIPCO, LLC, San Antonio, TX (US)
Filed on Aug. 29, 2022, as Appl. No. 17/822,880.
Claims priority of provisional application 63/238,850, filed on Aug. 31, 2021.
Int. Cl. G10L 13/00 (2006.01); G10L 13/033 (2013.01); G10L 25/78 (2013.01); G10L 15/02 (2006.01); G10L 15/22 (2006.01)
CPC G10L 13/033 (2013.01) [G10L 25/78 (2013.01); G10L 15/02 (2013.01); G10L 15/22 (2013.01)] 20 Claims
OG exemplary drawing
 
13. A system for automatically correcting an audio signal, the system comprising:
a device processor; and
a non-transitory computer readable medium storing instructions that are executable by the device processor to:
receive an audio signal;
detect a voice signal in the audio signal using a voice detection module;
analyze the audio signal, using a voice extraction module, and determine if the voice signal detected by the voice detection module can be extracted from the audio signal;
upon determining that the voice signal can be extracted from the audio signal, the instructions are further executable to:
extract the voice signal from the audio signal; and
generate a corrected audio signal using the extracted voice signal; and
upon determining that the voice signal cannot be extracted from the audio signal, the instructions are further executable to:
generate a synthesized voice signal;
synthesize an ambient noise present in the received audio signal; and
combine the synthesized voice signal with the synthesized ambient noise to generate a corrected audio signal in which both the synthesized voice signal and the synthesized ambient noise remain audible.