METHOD AND SERVER FOR WAVEFORM GENERATION Russian patent published in 2023 - IPC G06N3/08 G10L13/08 

Abstract RU 2803488 C2

FIELD: computer science.

SUBSTANCE: method includes obtaining a trained flow-based vocoder including reversible blocks and an untrained feed-forward vocoder including irreversible blocks that form a teacher-student network, performing a learning process on the teacher-student network, during which the server generates (i) a teacher-related waveform by a trained flow-based vocoder using the first spectrogram and the first input noise, (ii) a student-related waveform by an untrained feed-forward vocoder using the first spectrogram and the first input noise, and (iii) a loss value for a particular training iteration using the teacher-related waveform and the student-related waveform. The server then trains the untrained feed-forward vocoder to generate a waveform. The trained feed-forward vocoder is used instead of the trained flow-based vocoder to generate waveforms based on spectrograms and input noise.

EFFECT: improved efficiency of generating realistic audio representations of text.

17 cl, 7 dwg

Similar patents RU2803488C2

Title Year Author Number
TRAINING OF DNN-STUDENT BY MEANS OF OUTPUT DISTRIBUTION 2014
  • Chzhao Zhuj
  • Khuan Tszyuji-Tin
  • Li Tszinyuj
  • Gun Ifan
RU2666631C2
METHOD AND SERVER FOR DETERMINING TRAINING SET FOR MACHINE LEARNING ALGORITHM (MLA) TRAINING 2020
  • Dorogush Anna Veronika Yurevna
  • Alipov Vyacheslav Vyacheslavovich
  • Kruchinin Dmitriy Andreevich
  • Oganesyan Dmitry Alekseevich
RU2817726C2
METHODS AND ELECTRONIC DEVICES FOR PACKAGING REQUESTS INTENDED FOR PROCESSING BY PROCESSING UNIT 2021
  • Emelyanenko Dmitry Viktorovich
RU2810916C2
METHOD AND SERVER FOR TRAINING MACHINE LEARNING ALGORITHM IN TRANSLATION 2020
  • Dvorkovich Anton Aleksandrovich
  • Kovarsky Boris Andreevich
RU2770569C2
METHOD AND SERVER FOR CONVERTING TEXT TO SPEECH 2020
  • Chernenkov Dmitry Mikhailovich
  • Kirichenko Vladimir Vladimirovich
  • Baskov Ivan Sergeevich
  • Dzhunusov Sergey Nazimovich
RU2775821C2
ADAPTIVE AUDIO ENHANCEMENT FOR MULTICHANNEL SPEECH RECOGNITION 2016
  • Li, Bo
  • Weiss, Ron J.
  • Bacchiani, Michiel A.U.
  • Sainath, Tara N.
  • Wilson, Kevin William
RU2698153C1
METHOD FOR COMPRESSION OF NEURAL NETWORK MODEL AND METHOD AND APPARATUS FOR LANGUAGE CORPORA TRANSLATION 2019
  • Li Xiang
  • Sun Yuhui
  • Jiang Jialiang
  • Cui Jianwei
RU2749970C1
METHOD AND SERVER FOR TRAINING MACHINE LEARNING ALGORITHM IN OBJECT RANKING 2020
  • Ustimenko Aleksej Ivanovich
RU2782502C1
METHOD AND DEVICE FOR IMPROVING SPEECH SIGNAL USING FAST FOURIER CONVOLUTION 2022
  • Shchekotov Ivan Sergeevich
  • Andreev Pavel Konstantinovich
  • Alanov Aibek Arstanbekovich
  • Ivanov Oleg Yurievich
  • Vetrov Dmitry Petrovich
RU2795573C1
INTELLIGENT AUDIO-ANALYTICAL DEVICE AND METHOD FOR SPACECRAFTS 2019
  • Szurley Joseph
  • Das Samarjit
RU2793797C2

RU 2 803 488 C2

Authors

Kirichenko Vladimir Vladimirovich

Molchanov Aleksandr Aleksandrovich

Chernenkov Dmitry Mikhailovich

Babenko Artem Valerevich

Aliev Vladimir Andreevich

Baranchuk Dmitry Aleksandrovich

Dates

2023-09-14Published

2021-06-03Filed