US 12,437,735 B2
Beatboxing transcription
Bochen Li, Los Angeles, CA (US); Rodrigo Castellon, Los Angeles, CA (US); Daiyu Zhang, Los Angeles, CA (US); and Jitong Chen, Los Angeles, CA (US)
Assigned to LEMON INC., Grand Cayman (KY)
Filed by Lemon Inc., Grand Cayman (KY)
Filed on Mar. 7, 2022, as Appl. No. 17/688,382.
Prior Publication US 2023/0282188 A1, Sep. 7, 2023
Int. Cl. G10H 1/00 (2006.01); G10L 25/18 (2013.01); G10L 25/30 (2013.01)
CPC G10H 1/0008 (2013.01) [G10H 1/0066 (2013.01); G10L 25/18 (2013.01); G10L 25/30 (2013.01); G10H 2210/005 (2013.01); G10H 2210/056 (2013.01); G10H 2210/086 (2013.01); G10H 2250/311 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for generating a beatbox transcript, the method comprising:
receiving an audio signal having a plurality of beatbox sounds, wherein the plurality of beatbox sounds include beatbox vocals;
generating a spectrogram of the audio signal;
generating a beatbox sound activation map including a plurality of activation times for the plurality of beatbox sounds based on the spectrogram of the audio signal, further comprising processing the spectrogram of the audio signal with a neural network model trained on training samples that include sample beatbox sounds to generate the beatbox sound activation map including the plurality of activation times;
decoding the beatbox sound activation map into a beatbox transcript; and
providing the beatbox transcript as an output, wherein the beatbox transcript includes instrumental music matching the beatbox sound activation map.