FIELD: physics.
SUBSTANCE: group of inventions relates to acoustics. Audio data generator (10) can generate audio signal (16) from input signal (14) and target data (12) representing audio signal (16). It comprises first processing unit (40, 50, 50a-50h), receiving first data (15, 59a) extracted from input signal (14), and outputting first output data (69), second processing unit (45) receiving, as second data, first output data (69) or data extracted from first output data (69). First processing unit (50) comprises a conditioning set of training layers (71, 72, 73) configured to process target data (12) to obtain conditioning features parameters (74, 75), and styling element (77) configured to apply conditional feature parameters (74, 75) to first data (15, 59a) or to normalized first data (59, 76).
EFFECT: high quality of the generated audio signal.
38 cl, 7 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| AUDIO DATA GENERATOR AND METHODS OF GENERATING AUDIO SIGNAL AND TRAINING AUDIO DATA GENERATOR | 2021 |
|
RU2823015C1 |
| METHOD AND SERVER FOR WAVEFORM GENERATION | 2021 |
|
RU2803488C2 |
| METHOD AND DEVICE FOR IMPROVING SPEECH SIGNAL USING FAST FOURIER CONVOLUTION | 2022 |
|
RU2795573C1 |
| UNCONTROLLED VOICE RESTORATION USING UNCONDITIONED DIFFUSION MODEL WITHOUT TEACHER | 2023 |
|
RU2823017C1 |
| DEVICE, METHOD, OR COMPUTER PROGRAM FOR GENERATING AN EXTENDED-BAND AUDIO SIGNAL USING A NEURAL NETWORK PROCESSOR | 2018 |
|
RU2745298C1 |
| SYSTEMS AND METHODS OF AUDIO SIGNAL PRODUCTION | 2019 |
|
RU2804933C2 |
| METHOD FOR IMPROVING A SPEECH SIGNAL WITH A LOW DELAY, A COMPUTING DEVICE AND A COMPUTER-READABLE MEDIUM THAT IMPLEMENTS THE ABOVE METHOD | 2023 |
|
RU2802279C1 |
| ADAPTIVE AUDIO ENHANCEMENT FOR MULTICHANNEL SPEECH RECOGNITION | 2016 |
|
RU2698153C1 |
| TRAINING GAN (GENERATIVE ADVERSARIAL NETWORKS) TO CREATE PIXEL-BY-PIXEL ANNOTATION | 2019 |
|
RU2735148C1 |
| APPARATUS AND METHOD FOR ISOLATING SOURCES USING SOUND QUALITY ASSESSMENT AND CONTROL | 2019 |
|
RU2782364C1 |
