Speech quality measurement methods and models over ip-networks
Authors:
- Oleksandr Tymchenko,
- Orest Khamula,
- Bohdana Havrysh,
- Svitlana Vasiuta,
- Adam Jagiełło
Abstract
The MOS-based speech quality measurement methods allow us to determine generic encoder quality assessments on IP networks. However, they have several cautions to working within real-time, as they require the involvement of highly qualified experts. The paper considers alternative methods of quality assessment based on PESQ PSQM algorithms, taking into account network factors such as delay, jitter, and packet loss during network congestion. Also, the paper shows the efficiency of using MSE calculation. Conducted an experimental study of the relationship between MSE and PESQ score for different speech signal encoders and performed conversion of MSE – MOS. The results are easily adaptable to new types of encoders and to assess the deterioration of voice signal transmission when exposed to a variety of network factors.
- Record ID
- CUT86c28346e9e1416f8d215603a0e2be3c
- Publication categories
- ; ;
- Author
- Pages
- [1-6]
- Other elements of collation
- rys.; schem.; tab.; wykr.; Bibliografia (na s.) - [5-6]; Bibliografia (liczba pozycji) - 25; Oznaczenie streszczenia - Abstr.
- Book
- 2020 21st International Conference on Research and Education in Mechatronics (REM), Cracow, Poland, December 9th – 11th 2020, 2020, [S.l.], Institute of Electrical and Electronics Engineers, IEEE, [6] p., ISBN 978-1-7281-6224-9 (electronic)
- Keywords in English
- degradation, signal to noise ratio, IP networks, delays, speech coding, quality assessment, packet loss, subjective and objective methods, models, speech signals, quality measurement, communications systems
- DOI
- DOI:10.1109/REM49740.2020.9313079 Opening in a new tab
- URL
- https://ieeexplore.ieee.org/document/9313079 Opening in a new tab
- Language
- eng (en) English
- Score (nominal)
- 20
- Additional fields
- Indeksowana w: Web of Science, Scopus
- Uniform Resource Identifier
- https://cris.pk.edu.pl/info/article/CUT86c28346e9e1416f8d215603a0e2be3c/
- URN
urn:pkr-prod:CUT86c28346e9e1416f8d215603a0e2be3c
* presented citation count is obtained through Internet information analysis, and it is close to the number calculated by the Publish or PerishOpening in a new tab system.