US 12,406,656 B2
Spoken language recognition
Oriol Nieto-Caballero, Oakland, CA (US); Zeyu Jin, San Francisco, CA (US); Justin Jonathan Salamon, San Francisco, CA (US); and Franck Dernoncourt, Spokane, WA (US)
Assigned to ADOBE INC., San Jose, CA (US)
Filed by ADOBE INC., San Jose, CA (US)
Filed on Feb. 1, 2023, as Appl. No. 18/104,434.
Prior Publication US 2024/0257798 A1, Aug. 1, 2024
Int. Cl. G10L 25/30 (2013.01); G10L 15/00 (2013.01)
CPC G10L 15/005 (2013.01) [G10L 25/30 (2013.01)] 20 Claims
OG exemplary drawing
 
1. One or more computer storage media storing computer-useable instructions that, when used by a computing device, cause the computing device to perform operations, the operations comprising:
generating features from an audio signal comprising speech;
providing the features as input to a neural network having one or more convolutional layers and an output activation layer, each neuron of the output activation layer corresponding to a language from a set of languages and generating an activation value; and
providing an indication of zero or more languages from the set of languages based on the activation value for each neuron of the output activation layer and an activation threshold value.