公开(公告)号：US20230154451A1

公开(公告)日：2023-05-18

申请号：US17525814

申请日：2021-11-12

Applicant: LEMON INC.

Inventor： Lamtharn HANTRAKUL ,  Siyuan Shan ,  Jitong Chen ,  Matthew David Avent ,  David Trevelyan

IPC: G10L13/04 ,  G06N20/00

CPC classification number: G10L13/04 ,  G06N20/00

Abstract: The present disclosure describes techniques for differentiable wavetable synthesizer. The techniques comprise extracting features from a dataset of sounds, wherein the features comprise at least timbre embedding; input the features to the first machine learning model, wherein the first machine learning model is configured to extract a set of N×L learnable parameters, N represents a number of wavetables, and L represents a wavetable length; outputting a plurality of wavetables, wherein each of plurality of wavetables comprises a waveform associated with a unique timbre, the plurality of wavetables form a dictionary, and the plurality of wavetables are portable to perform audio-related tasks.

公开(公告)号：US20230282188A1

公开(公告)日：2023-09-07

申请号：US17688382

申请日：2022-03-07

Applicant: Lemon Inc.

Inventor： Bochen Li ,  Rodrigo Castellon ,  Daiyu Zhang ,  Jitong Chen

IPC: G10H1/00 ,  G10L25/18 ,  G10L25/30

CPC classification number: G10H1/0008 ,  G10H1/0066 ,  G10L25/18 ,  G10L25/30 ,  G10H2250/311 ,  G10H2210/005 ,  G10H2210/086 ,  G10H2210/056

Abstract: Methods, systems, and storage media for generating a beatbox transcript are disclosed. Some examples may include: receiving an audio signal having a plurality of beatbox sounds, generating a spectrogram of the audio signal, processing the spectrogram of the audio signal with a neural network model trained on training samples including beatbox sounds, generating, by the neural network model a beatbox sound activation map including a plurality of activation times for a plurality of beatbox sounds, decoding the beatbox sound activation map into a beatbox transcript and providing the beatbox transcript as an output.

公开(公告)号：US12198673B2

公开(公告)日：2025-01-14

申请号：US17525814

申请日：2021-11-12

Applicant: LEMON INC.

Inventor： Lamtharn Hantrakul ,  Siyuan Shan ,  Jitong Chen ,  Matthew David Avent ,  David Trevelyan

IPC: G10L13/04 ,  G06N20/00 ,  G10H7/10 ,  G10L13/047 ,  G10L13/08 ,  G10L15/04 ,  G10L19/26

Abstract: The present disclosure describes techniques for differentiable wavetable synthesizer. The techniques comprise extracting features from a dataset of sounds, wherein the features comprise at least timbre embedding; input the features to the first machine learning model, wherein the first machine learning model is configured to extract a set of N×L learnable parameters, N represents a number of wavetables, and L represents a wavetable length; outputting a plurality of wavetables, wherein each of plurality of wavetables comprises a waveform associated with a unique timbre, the plurality of wavetables form a dictionary, and the plurality of wavetables are portable to perform audio-related tasks. Finally, the said wavetables are used to initialize another machine learning model so as to help reduce computational complexity of an audio synthesis obtained as output of the another machine learning model.

公开(公告)号：US12040000B2

公开(公告)日：2024-07-16

申请号：US18366478

申请日：2023-08-07

Applicant: Lemon Inc.

Inventor： Chenyu Sun ,  Jitong Chen ,  Nathanael Schager ,  Maryyann Crichton ,  Josiah John Serrano ,  Bochen Li ,  Xuefan Hu ,  Fraser Smith ,  Hwankyoo Shawn Kim ,  David Trevelyan ,  Suiyu Feng ,  Brandon Wu ,  Tao Xiong

IPC: G11B27/031 ,  G06F3/04847 ,  G06F3/0488 ,  G11B27/00 ,  G06F3/16

CPC classification number: G11B27/031 ,  G06F3/04847 ,  G06F3/0488 ,  G11B27/007 ,  G06F3/165

Abstract: The present application provides a special effect processing method and apparatus. The method includes: generating an audio signal in response to a touch operation of a user in a process of playing a video; segmenting the audio signal into multiple audio frames; performing, according to attributes of the audio frames, special effect processing on a picture which is currently played in the video.

公开(公告)号：US20230197040A1

公开(公告)日：2023-06-22

申请号：US17556178

申请日：2021-12-20

Applicant: Lemon Inc.

Inventor： Bochen Li ,  Daiyu Zhang ,  Shawn Chan Zhen Yi ,  Jitong Chen

IPC: G10H1/00 ,  G06V40/16 ,  G06V40/20

CPC classification number: G10H1/0008 ,  G06V40/174 ,  G06V40/20 ,  G10H2250/311 ,  G10H2210/325 ,  G10H2210/571 ,  G10H2220/106 ,  G10H2220/201 ,  G10H2220/455 ,  G10H2210/105

Abstract: A method for generating an audio output is described. Image inputs of interactive movements by a user captured by an image sensor are received. The interactive movements are mapped to a sequence of audio element identifiers. The sequence of audio element identifiers are processed to generate a musical sequence by performing music theory rule enforcement on the sequence of audio element identifiers. An audio output that represents the musical sequence is generated.