Slika naslovnice

Speech quality classifier model based on DBN that considers atmospheric phenomena

Current implementations of 5G networks consider higher frequency range of operation than previous telecommunication networks, and it is possible to offer higher data rates for different applications. On the other hand, atmospheric phenomena could have a more negative impact on the transmission quali...

Full description

Permalink: http://skupni.nsk.hr/Record/nsk.NSK01001102369/Details
Matična publikacija: Journal of communications software and systems (Online)
16 (2020), 1 ; str. 75-84
Glavni autori: Silva, Marielle Jordane da (Author), Melgarejo, Dick Carrillo, Rosa, Renata Lopes, Rodríguez, Demóstenes Zegarra
Vrsta građe: e-članak
Jezik: eng
Predmet:
Bežične komunikacije > Kvaliteta govora > Atmosferske prilike > 5G mreža > Frekvencije
Online pristup: https://doi.org/10.24138/jcomss.v16i1.1033
Journal of communications software and systems (Online)
Hrčak
LEADER 03153naa a22003974i 4500
001 NSK01001102369
003 HR-ZaNSK
005 20210722111636.0
006 m d
007 cr||||||||||||
008 210527s2020 ci d |o |0|| ||eng
024 7 |2 doi  |a 10.24138/jcomss.v16i1.1033 
035 |a (HR-ZaNSK)001102369 
040 |a HR-ZaNSK  |b hrv  |c HR-ZaNSK  |e ppiak 
041 0 |a eng  |b eng 
042 |a croatica 
044 |a ci  |c hr 
080 1 |a 004  |2 2011 
080 1 |a 621.3  |2 2011 
100 1 |a Silva, Marielle Jordane da  |4 aut  |9 HR-ZaNSK 
245 1 0 |a Speech quality classifier model based on DBN that considers atmospheric phenomena  |h [Elektronička građa] /  |c Marielle Jordane da Silva, Dick Carrillo Melgarejo, Renata Lopes Rosa, Demóstenes Zegarra Rodríguez. 
300 |b Graf. prikazi. 
504 |a Bibliografija: 55 jed. 
504 |a Summary. 
520 |a Current implementations of 5G networks consider higher frequency range of operation than previous telecommunication networks, and it is possible to offer higher data rates for different applications. On the other hand, atmospheric phenomena could have a more negative impact on the transmission quality. Thus, the study of the transmitted signal quality at high frequencies is relevant to guaranty the user ́s quality of experience. In this research, the recommendations ITU-R P.838-3 and ITU-R P.676-11 are implemented in a network scenario, which are methodologies to estimate the signal degradations originated by rainfall and atmospheric gases, respectively. Thus, speech signals are encoded by the AMR-WB codec, transmitted and the perceptual speech quality is evaluated using the algorithm described in ITU-T Rec. P.863, mostly known as POLQA. The novelty of this work is to propose a non-intrusive speech quality classifier that considers atmospheric phenomena. This classifier is based on Deep Belief Networks (DBN) that uses Support Vector Machine (SVM) with radial basis function kernel (RBF-SVM) as classifier, to identify five predefined speech quality classes. Experimental Results show that the proposed speech quality classifier reached an accuracy between 92% and 95% for each quality class overcoming the results obtained by the sole non-intrusive standard described in ITU-T Recommendation P.563. Furthermore, subjective tests are carried out to validate the proposed classifier performance, and it reached an accuracy of 94.8%. 
653 0 |a Bežične komunikacije  |a Kvaliteta govora  |a Atmosferske prilike  |a 5G mreža  |a Frekvencije 
700 1 |a Melgarejo, Dick Carrillo  |4 aut  |9 HR-ZaNSK 
700 1 |a Rosa, Renata Lopes  |4 aut  |9 HR-ZaNSK 
700 1 |a Rodríguez, Demóstenes Zegarra  |4 aut  |9 HR-ZaNSK 
773 0 |t Journal of communications software and systems (Online)  |x 1846-6079  |g 16 (2020), 1 ; str. 75-84  |w nsk.(HR-ZaNSK)000644741 
981 |b Be2020  |b B03/20 
998 |b dalo2107 
856 4 0 |u https://doi.org/10.24138/jcomss.v16i1.1033 
856 4 0 |u https://jcomss.fesb.unist.hr/index.php/jcomss/article/view/1033  |y Journal of communications software and systems (Online) 
856 4 0 |u https://hrcak.srce.hr/236753  |y Hrčak 
856 4 1 |y Digitalna.nsk.hr 

Slični primjerci