Influencing Factors in Speech Quality Assessment using Crowdsourcing

This book evaluates the impact of relevant factors affecting the results of speech quality assessment studies carried out in crowdsourcing. The author describes how these factors relate to the test structure, the effect of environmental background noise, and the influence of language differences. He details multiple user-centered studies that have been conducted to derive guidelines for reliable collection of speech quality scores in crowdsourcing. Specifically, different questions are addressed such as the optimal number of speech samples to include in a listening task, the influence of the environmental background noise in the speech quality ratings, as well as methods for classifying background noise from web audio recordings, or the impact of language proficiency in the user perception of speech quality. Ultimately, the results of these studies contributed to the definition of the ITU-T Recommendation P.808 that defines the guidelines to conduct speech quality studies in crowdsourcing.

Presents findings from ITU-T Recommendation P.808 which sets the methodology Includes a framework to collects reliable speech quality scores in crowdsourcing Provides two datasets of labeled environmental background noises that were collected through the audio web-API

Auteur
Rafael Zequeira Jiménez received a M.Sc. degree as Telecommunication Engineer at the University of Granada, Spain in 2014. In 2015, he joined the Quality and Usability Lab at the Berlin Institute of Technology, working as a research assistant. His research focused on the impact of the main influencing factors in speech quality assessment studies using crowdsourcing. Rafael was a member of the Study Group 12 of the ITU-T Standardization Sector. He actively contributed to the standardization of methods for speech quality assessment in crowdsourcing environments, materialized as the ITU-T Recommendation P.808. He was also awarded with an education program funded by the German Federal Ministry of Education and Research. This program is intended to train and professionally develop the next generation of IT leaders in Germany. Rafael completed his PhD in computer science at the Berlin Institute of Technology in 2021.

Contenu
Introduction.- Related Work.- Method.- Test Structure.- Impact of Background Noise.- Influence of Language.- Conclusion. <p