METHODS OF TRAINING MODEL AND VOICE CONVERSION AND DEVICE, OTHER DEVICE AND DATA MEDIUM Russian patent published in 2024 - IPC G10L13/02 G10L15/18 

Abstract RU 2830834 C2

FIELD: computer engineering.

SUBSTANCE: invention relates to computer engineering for processing audio data. Result is achieved by steps of obtaining a first voice characteristic from any audio sample fragment using a voice extraction network in an initial voice conversion model; obtaining a first semantic characteristic based on a first voice characteristic and a linear spectrogram corresponding to the audio data sample using a voice removal network in the original voice conversion model, wherein the first semantic characteristic is a characteristic of the audio data sample, which is not associated with the speaker’s voice, but with semantic information; obtaining synthesized audio data based on a first semantic characteristic and a second voice characteristic of the target audio data corresponding to the audio data sample using a vocoder in the original voice conversion model; and obtaining a trained voice conversion model by training the initial voice conversion model based on the target audio data and the synthesized audio data corresponding to each audio data sample fragment.

EFFECT: high accuracy of content information of an initial audio signal during voice conversion.

18 cl, 8 dwg

Similar patents RU2830834C2

Title Year Author Number
UNCONTROLLED VOICE RESTORATION USING UNCONDITIONED DIFFUSION MODEL WITHOUT TEACHER 2023
  • Andreev Pavel Konstantinovich
  • Iashchenko Anastasia Sergeevna
  • Shchekotov Ivan Sergeevich
  • Babaev Nicholas Andrew
RU2823017C1
AUDIO DATA GENERATOR AND METHODS OF GENERATING AUDIO SIGNAL AND TRAINING AUDIO DATA GENERATOR 2021
  • Ahmed, Ahmed Mustafa Mahmoud
  • Pia, Nicola
  • Fuchs, Guillaume
  • Multrus, Markus
  • Korse, Srikanth
  • Gupta, Kishan
  • Buethe, Jan
RU2823015C1
METHOD FOR SPEECH SYNTHESIS WITH TRANSMISSION OF ACCURATE INTONATION OF THE CLONED SAMPLE 2020
  • Tagunov Petr Vladimirovich
  • Gonta Vladislav Aleksandrovich
RU2754920C1
AUDIO DATA GENERATOR AND METHODS OF GENERATING AUDIO SIGNAL AND TRAINING AUDIO DATA GENERATOR 2021
  • Ahmed, Ahmed Mustafa Mahmoud
  • Pia, Nicola
  • Fuchs, Guillaume
  • Multrus, Markus
  • Korse, Srikanth
  • Gupta, Kishan
  • Buethe, Jan
RU2823016C1
TEXT-DEPENDENT VOICE CONVERSION METHOD 2010
  • Bredikhin Aleksandr Jur'Evich
  • Petrovskij Aleksandr Aleksandrovich
  • Sergejchev Nikolaj Evgen'Evich
RU2427044C1
METHOD FOR AUDIOVISUAL RECOGNITION OF PERSONAL PROTECTION EQUIPMENT ON HUMAN FACE 2022
  • Riumina Elena Vitalevna
  • Markitantov Maksim Viktorovich
  • Riumin Dmitrii Aleksandrovich
  • Karpov Aleksei Anatolevich
RU2791415C1
METHOD AND SERVER FOR SPEECH SYNTHESIS IN TEXT 2015
  • Edrenkin Ilya Vladimirovich
RU2632424C2
METHOD OF RE-SOUNDING AUDIO MATERIALS AND APPARATUS FOR REALISING SAID METHOD 2012
  • Bredikhin Aleksandr Jur'Evich
RU2510954C2
METHOD AND SERVER FOR WAVEFORM GENERATION 2021
  • Kirichenko Vladimir Vladimirovich
  • Molchanov Aleksandr Aleksandrovich
  • Chernenkov Dmitry Mikhailovich
  • Babenko Artem Valerevich
  • Aliev Vladimir Andreevich
  • Baranchuk Dmitry Aleksandrovich
RU2803488C2
SPEECH SYNTHESIS AND CODING METHODS 2010
  • Drugman Thomas
  • Wilfart Geoffrey
  • Dutoit Thierry
RU2557469C2

RU 2 830 834 C2

Authors

Huang, Jiahong

Li, Yule

Xiang, Wei

Dates

2024-11-26Published

2022-12-20Filed