Overview
- Presents the overview of a technical setup of a simulation able to replicate individual interactions
- Includes insights into the changes of individual interactions that occur due to delay and packet loss
- Describes and extends the state-of-the-art in parametric speech quality prediction
Part of the book series: T-Labs Series in Telecommunication Services (TLABS)
Access this book
Tax calculation will be finalised at checkout
Other ways to access
Table of contents (7 chapters)
Keywords
About this book
This book discusses the simulation of conversations through a novel approach of predicting speech quality based on the interactions of two simulated interlocutors. The author describes the setup of a simulation environment that is capable of simulating human dialogue on the speech level. The impact of delay and bursty packet loss on VoIP conversations is investigated and modeled for the use in the simulation. Based on parameters extracted from simulated conversations, the author proposes extensions to the E-model, a parametric model standardized by the International Telecommunications Union, in order to predict the quality of the simulated conversations. The author shows that predictions based on the simulated conversations outperform models that rely on the transmission parameters alone.
Authors and Affiliations
About the author
Thilo Michael received his B.Sc. in Applied Computer Science at the Baden-Wuerttemberg Cooperative State University (DHBW) while working at IBM Germany. He obtained his M.Sc. in Computer Science at the Technische Universität Berlin, which focused on natural language processing and spoken dialogue systems. From 2017 on, he was employed at the Quality and Usability Lab at TU Berlin, where he finished his PhD on the simulation of conversations. As an invited speaker he held presentations on the topics of incremental spoken dialogue and chatbots.
Bibliographic Information
Book Title: Simulating Conversations for the Prediction of Speech Quality
Authors: Thilo Michael
Series Title: T-Labs Series in Telecommunication Services
DOI: https://doi.org/10.1007/978-3-031-31844-3
Publisher: Springer Cham
eBook Packages: Engineering, Engineering (R0)
Copyright Information: The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2023
Hardcover ISBN: 978-3-031-31843-6Published: 02 July 2023
Softcover ISBN: 978-3-031-31846-7Due: 01 August 2023
eBook ISBN: 978-3-031-31844-3Published: 30 June 2023
Series ISSN: 2192-2810
Series E-ISSN: 2192-2829
Edition Number: 1
Number of Pages: XVI, 152
Number of Illustrations: 7 b/w illustrations, 80 illustrations in colour
Topics: Signal, Image and Speech Processing, User Interfaces and Human Computer Interaction, Natural Language Processing (NLP), Engineering Acoustics