Inhalt des Dokuments
- © Copyright??
Multimodal Quality Assessment on Videoconferencing
Benjamin was born in France in 1983. He first studied general Mathematics and Physics in Toulouse. Then he joined the National School of Higher Education in Physics of Strasbourg (Engineering school) and specialized in Video and Image Processing. He carried out his master's degree within the INRIA in cooperation with the LIAMA (Beijing) on "Structural Change Detectection on Satellite Images using Conditional Mixed States Markovian Model". In 2007, he started a Phd within the Deutsche Telekom Laboratories and the Technical University of Berlin.
Address Quality and Usability Lab
Deutsche Telekom Laboratories
D-10587 Berlin, Germany Tel: +49 30 8353 58233
|Autor||Belmudez, Benjamin and Lewcio, Blazej and Möller, Sebastian|
|Journal||Acta Acustica united with Acustica|
|Zusammenfassung||In this study we present an evaluation and improvement of time integration speech quality models applied to assess fluctuating quality of audiovisual transmission. We first introduce a subjective test methodology to evaluate the user perception of time-varying quality of 90 seconds long sequences that are organized in a simulated conversational structure. We conducted a two-fold user test where in the first part, the quality of simulated video-telephony conversations was assessed. Audiovisual impairments were temporally distributed to follow predefined quality profiles. In the second part of the experiment, subjective ratings of short audiovisual samples (9 seconds) constituent of the simulated conversations are gathered. The results of both experiments show that the end-dialog judgments are closely correlated to the plain average of the short samples. The modeling results for call quality models that predict the quality at the end of a (simulated) conversation are described. These models proved to enhance the prediction accuracy in comparison to the plain average, and an optimization of the models' parameters further refines the correlation of the estimates with the subjective data. The optimized models also showed a higher correlation and a lower prediction error on independent test data.|