Detail publikace

Single-Channel Speech Quality Enhancement in Mobile Networks Based on Generative Adversarial Networks

WU, G. HERENCSÁR, N.

Originální název

Single-Channel Speech Quality Enhancement in Mobile Networks Based on Generative Adversarial Networks

Typ

článek v časopise ve Web of Science, Jimp

Jazyk

angličtina

Originální abstrakt

A large amount of randomly generated noise in mobile networks leads to a lack of targeting and gaming processes in the speech enhancement process, and the enhancement process from the perspective of acoustic features alone suffers from major drawbacks. Propose a single-channel speech quality enhancement method based on generative adversarial networks in mobile networks. Explain the principle of generative adversarial network to realize single-channel speech quality enhancement in mobile networks and clarify its shortcomings. Design an improved Mel frequency cepstral coefficient extraction method to extract 12 base features as the enhancement basis. Use the relative average least squares loss instead of the traditional loss function to enhance the training efficiency, use the hybrid penalty term to enhance the generator's ability to generate single-channel speech, and optimize the discriminator through the multi-layer convolution and the addition of fully connected layers to enhance the speech quality enhancement ability of adversarial generative networks in various aspects, forming a relative average generative adversarial network (RaGAN) based on hybrid penalty term to realize single-channel speech quality enhancement processing. Through the experiment, when the discriminator is applied with the size of a 3*3 convolutional kernel, the best effect of speech quality enhancement is achieved in the mobile network. This method can complete the enhancement of single-channel speech quality in the mobile network, and the effect is significant, which can effectively reduce the noise in the original single-channel speech.

Klíčová slova

Generative adversarial networks; RaGAN; Hybrid penalty term; Single-channel; Speech quality; Discriminator; Mobile networks

Autoři

WU, G.; HERENCSÁR, N.

Vydáno

2. 4. 2024

Nakladatel

SPRINGER

Místo

NEW YORK

ISSN

1572-8153

Periodikum

Mobile Networks and Applications

Ročník

2024

Číslo

neuvedeno

Stát

Nizozemsko

Strany od

1

Strany do

15

Strany počet

15

URL

Plný text v Digitální knihovně

BibTex

@article{BUT188428,
  author="Guifen {Wu} and Norbert {Herencsár}",
  title="Single-Channel Speech Quality Enhancement in Mobile Networks Based on Generative Adversarial Networks",
  journal="Mobile Networks and Applications",
  year="2024",
  volume="2024",
  number="neuvedeno",
  pages="15",
  doi="10.1007/s11036-024-02300-4",
  issn="1572-8153",
  url="https://link.springer.com/article/10.1007/s11036-024-02300-4"
}