FIELD: computer technology; processing audio signals.
SUBSTANCE: technical result is achieved by generating a primary signal having a frequency range extension, and frequency range extension is not included in the frequency range of the input audio signal; generating a parametric representation for frequency range extension using the frequency range of the input audio signal and the trained neural network; and processing the primary signal using a parametric representation for the expansion frequency range to obtain a processed primary signal having frequency components in the expansion frequency range.
EFFECT: technical result is to provide the principle of improved generation of an audio signal with an extended band.
34 cl, 23 dwg
Title | Year | Author | Number |
---|---|---|---|
ADAPTIVE AUDIO ENHANCEMENT FOR MULTICHANNEL SPEECH RECOGNITION | 2016 |
|
RU2698153C1 |
MODULE FOR ASSESSMENT OF SIMILARITY OF AUDIO SIGNALS, AUDIO ENCODER, METHODS AND COMPUTER PROGRAM | 2019 |
|
RU2782981C2 |
AUDIO ENCODER AND DECODER USING FREQUENCY DOMAIN PROCESSOR WITH FULL-BAND GAP FILLING AND TIME DOMAIN PROCESSOR | 2015 |
|
RU2671997C2 |
AUDIO SIGNAL CODING AND DECODING DEVICE USING FREQUENCY-DOMAIN PROCESSOR, TIME-DOMAIN PROCESSOR AND CROSS-PROCESSOR FOR CONTINUOUS INITIALIZATION | 2015 |
|
RU2668397C2 |
METHOD AND APPARATUS FOR DEFINING A DEEP FILTER | 2020 |
|
RU2788939C1 |
OPTICAL CHARACTER RECOGNITION BY MEANS OF COMBINATION OF NEURAL NETWORK MODELS | 2020 |
|
RU2768211C1 |
BANDWIDTH EXPANSION DEVICE | 2010 |
|
RU2552184C2 |
METHOD OF MULTIMODAL CONTACTLESS CONTROL OF MOBILE INFORMATION ROBOT | 2020 |
|
RU2737231C1 |
DECISION ON PRESENCE/ABSENCE OF VOCALIZATION FOR SPEECH PROCESSING | 2014 |
|
RU2636685C2 |
METHODS AND ELECTRONIC DEVICES FOR PACKAGING REQUESTS INTENDED FOR PROCESSING BY PROCESSING UNIT | 2021 |
|
RU2810916C2 |
Authors
Dates
2021-03-23—Published
2018-04-13—Filed