In the realm of real-time communications, WebRTC-based multimedia applications are increasingly prevalent as these can be smoothly integrated within Web browsing sessions. The browsing experience is then significantly improved with respect to scenarios where browser add-ons and/or plug-ins are used; still, the end user's Quality of Experience (QoE) in WebRTC sessions may be affected by network impairments, such as delays and losses. Due to the variability in user perceptions under different communications scenarios, comprehending and enhancing the resulting service quality is a complex endeavor. To address this, we present a dataset that provides a comprehensive perspective on the conversational quality of a two-party WebRTC-based audiovisual telemeeting service. This dataset was gathered through subjective evaluations involving 20 subjects across 15 different test conditions (TCs). A specialized system was developed to induce controlled network disruptions such as delay, jitter, and packet loss rate, which adversely affected the communication between the parties. This methodology offered an insight into user perceptions under various network impairments. The dataset encompasses a blend of objective and subjective data including ACR (Absolute Category Rating) subjective scores, WebRTC-internals parameters, facial expressions features, and speech features. Consequently, it serves as a substantial contribution to the improvement of WebRTC-based video call systems, offering practical and real-world data that can drive the development of more robust and efficient multimedia communication systems, thereby enhancing the user's experience.

WebRTC-QoE: A dataset of QoE assessment of subjective scores, network impairments, and facial & speech features

Bingol, Gulnaziye;Porcu, Simone;Floris, Alessandro
;
Atzori, Luigi
2024-01-01

Abstract

In the realm of real-time communications, WebRTC-based multimedia applications are increasingly prevalent as these can be smoothly integrated within Web browsing sessions. The browsing experience is then significantly improved with respect to scenarios where browser add-ons and/or plug-ins are used; still, the end user's Quality of Experience (QoE) in WebRTC sessions may be affected by network impairments, such as delays and losses. Due to the variability in user perceptions under different communications scenarios, comprehending and enhancing the resulting service quality is a complex endeavor. To address this, we present a dataset that provides a comprehensive perspective on the conversational quality of a two-party WebRTC-based audiovisual telemeeting service. This dataset was gathered through subjective evaluations involving 20 subjects across 15 different test conditions (TCs). A specialized system was developed to induce controlled network disruptions such as delay, jitter, and packet loss rate, which adversely affected the communication between the parties. This methodology offered an insight into user perceptions under various network impairments. The dataset encompasses a blend of objective and subjective data including ACR (Absolute Category Rating) subjective scores, WebRTC-internals parameters, facial expressions features, and speech features. Consequently, it serves as a substantial contribution to the improvement of WebRTC-based video call systems, offering practical and real-world data that can drive the development of more robust and efficient multimedia communication systems, thereby enhancing the user's experience.
2024
WebRTC
Quality of experience
Network impairments
Facial expressions
Speech
WebRTC-internals
File in questo prodotto:
File Dimensione Formato  
pub-WebRTC-QoE dataset.pdf

Solo gestori archivio

Descrizione: VoR
Tipologia: versione editoriale (VoR)
Dimensione 3.42 MB
Formato Adobe PDF
3.42 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
pp2024-comnet_webrtc-qoe dataset_with_cover.pdf

embargo fino al 27/03/2025

Descrizione: AAM
Tipologia: versione post-print (AAM)
Dimensione 718.73 kB
Formato Adobe PDF
718.73 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11584/395083
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact