Plenary Lecture

Recent Advances in Speech Quality Assessment

Associate Professor Miroslav Voznak
Department of Telecommunications
Faculty of Electrical Engineering and Computer Science
VSB-Technical University of Ostrava
Czech Republic
E-mail: voznak@ieee.org

Abstract: This keynote will deal with new approaches to speech quality assessment, especially with non-intrusive methods which are suitable for speech quality evaluation in real-time communication. The first part will discuss conventional models of objective speech quality assessment based on evaluation of signals in time-frequency domain. This way is applied in algorithms such as PESQ (Perceptual Evaluation of Speech Quality) or recently standardized POLQA (Perceptual Objective Listening Quality Assessment). The second part of the keynote speech will deal with an intrusive approach known as E-model andwith proposal of the original E-model modification. The new model includes improvements giving more precise results when a jitter is present in transmission channel. The idea is based on the fact that the network jitter can affect overall delay in delivery or a packet loss due to a limitation of play-out buffer in IP phones or VoIP gateways. Delay is incorporated in an impairment factor Id of E-model whereas losses are issue of Ie-eff parameter in E-model. There will be presented how the estimated speech quality is affected by jitter and the computed results in E-model will be compared with values gained by PESQ objective intrusive method. The last part will discuss a practical implementation of computational E-model in BESIP (Bright Embedded Solution for IP telephony) where a monitoring module has been implemented, the BESIP consists of four modules and the speech quality assessment is a part of one of them. In order to verify suitability of the applied method in Monitoring module, a comparison to the objective intrusive PESQ method was carried out. In addition to this module, the entire concept of BESIP project will be introduced and a roadmap of next development.

Brief Biography of the Speaker: Miroslav VOZNAK (born in 1971) is an Associate professor with Department of Telecommunications, VSB-Technical University of Ostrava. He received his M.S. and Ph.D. degrees in telecommunications, dissertation thesis “Voice traffic optimization with regard to speech quality in network with VoIP technology” from the VSB-Technical University of Ostrava, in 1995 and 2002, respectively. Topics of his research interests are Next Generation Networks, IP telephony, speech quality and network security. He is a member of INDECT team conducted by AGH University of Science and Technology in Cracow (7 FP EU project 2009-2013 under Grant Agreement No. 218086), the purpose of the INDECT project is to involve European scientists and researchers in the development of solutions to and tools for automatic threat detection. He is also a member of team Softcomputing involved in IT4Innovations, Czech National Centre ofExcellence in Ostrava. He is author or co-author more than 200 results indexed in Czechnational database of Research, Development andInnovations, single author more than 70 of them and three college books. Miroslav Voznak is also author or co-author more than 50 results indexed in SciVer SCOPUS in last five years, with more than 100 citations and h-index = 6and about 400 registered citations in Google Scholar with h-index=10 in last five years.He is in editorial boards of several journals such as “Radioengineering“, “Embedded and Distributed Systems“ and“Advances in Electrical andElectronic Engineering“. Since 2013 he also has served as department chair of Dpt. of Telecommunications in VSB-Technical University of Ostrava.

Bulletin Board


The conference program is online.

The Conference Guide is online.

The paper submission deadline has expired. Please choose a future conference to submit your paper.

WSEAS Main Site

NAUN Main Site

Publication Ethics and Malpractice Statement