Evaluation of Speech Quality Degradation due to Atmospheric Phenomena

Silva, Marielle J. da; Begazo, Dante Coaquira; Rodríguez, Demóstenes Zegarra

doi:10.23919/softcom.2019.8903693

Cited by 1 publication

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [28], the behavior of signal attenuation (dB/Km) in the frequency range of 10 to 100 GHz due to atmospheric gases is presented as can be observed in Fig. 3.…”

Section: A Impact Of Rain and Atmospheric Gases On Speech Qualitymentioning

confidence: 99%

“…• A proposed speech quality classifier model that considers atmospheric phenomena parameters and speech codec characteristics, which is based on Deep Belief Networks (DBN) with RBF-SVM. It is important to note that this proposed model analyze the speech signal itself, different that the solution proposed in [28] that considered a network parametric approach. It is worth noting that the proposed model estimates a perceptual speech quality class, and its main goal is to be useful in wireless network transmission monitoring tasks.…”

Section: Introductionmentioning

confidence: 96%

“…In this arena, this research presents additional contributions regarding [28], which can be summarized as follows:…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Speech Quality Classifier Model based on DBN that Considers Atmospheric Phenomena

Silva

Carrillo²,

Rosa

et al. 2020

J. commun. softw. syst. (Online)

View full text Add to dashboard Cite

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%.

show abstract

“…In [28], the behavior of signal attenuation (dB/Km) in the frequency range of 10 to 100 GHz due to atmospheric gases is presented as can be observed in Fig. 3.…”

Section: A Impact Of Rain and Atmospheric Gases On Speech Qualitymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 96%