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, including test structure, environmental background noise, and language differences. It provides guidelines for reliable collection of speech quality scores through user-centered studies and contributes to the definition of the ITU-T Recommendation P.808.

Format: Hardback
Length: 116 pages
Publication date: 05 April 2022
Publisher: Springer Nature Switzerland AG

This comprehensive book delves into the profound impact of various factors on the outcomes of speech quality assessment studies conducted in the realm of crowdsourcing. The author intricately explores the intricate relationships between these factors and the test structure, the influence of environmental background noise, and the ramifications of language differences. Through a series of user-centered studies, the author presents valuable guidelines for the reliable collection of speech quality scores in crowdsourcing. These studies address critical questions such as the optimal number of speech samples to include in a listening task, the profound impact of environmental background noise on speech quality ratings, and innovative methods for classifying background noise from web audio recordings. Furthermore, the book sheds light on the influence of language proficiency on the user perception of speech quality, highlighting the need for tailored approaches to ensure accurate assessments across diverse linguistic backgrounds.

The culmination of these studies culminates in the formulation of the ITU-T Recommendation P.808, a seminal document that establishes comprehensive guidelines for conducting speech quality studies in crowdsourcing. This recommendation serves as a valuable resource for researchers, practitioners, and industry professionals seeking to harness the power of crowdsourcing for speech quality assessment and improvement.

By examining these critical aspects, this book offers a comprehensive understanding of the challenges and opportunities inherent in speech quality assessment studies in crowdsourcing, paving the way for future research and innovation in this field.

Weight: 377g
Dimension: 235 x 155 (mm)
ISBN-13: 9783030933098
Edition number: 1st ed. 2022