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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F24%3APU151188" target="_blank" >RIV/00216305:26220/24:PU151188 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/article/10.1007/s11036-024-02300-4" target="_blank" >https://link.springer.com/article/10.1007/s11036-024-02300-4</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s11036-024-02300-4" target="_blank" >10.1007/s11036-024-02300-4</a>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20200 - Electrical engineering, Electronic engineering, Information engineering

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Mobile Networks and Applications

ISSN

1383-469X

e-ISSN

1572-8153

Svazek periodika

2024

Číslo periodika v rámci svazku

neuvedeno

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

15

Strana od-do

1-15

Kód UT WoS článku

001195684700001

EID výsledku v databázi Scopus

2-s2.0-85189202848