While previous research has shown that streaming media can respond to network congestion, it is not known to what extent commercial products are responsive. Knowledge of streaming media’s response to congestion encountered in the network is important in building networks that better accommodate their turbulence. This research seeks to characterize the bitrate response of Windows Streaming Media (WSM) in response to network-level metrics such as capacity, loss rate, and round-trip time. We construct a streaming media test bed that allows us to systematically vary network and content encoding characteristics to measure WSM congestion responsiveness under various streaming configurations and network conditions. We find WSM has a prominent buffering phase in which it sends data at a bitrate significantly higher than the steady-state playout rate. Overall, WSM is responsive to available capacity, but is often unfair to TCP. The additional characteristics we measure can be combined to guide emulation or simulation configurations and network traffic generators for use in further research. The corpus includes new annotations for affect magnitude detection, anaphora resolution, and speech processing. The corpus includes new automatic annotations using Natural Language Processing toolkits as well as new manual annotations for affect magnitude detection.
The files are available for download via HTTP. Link: http://web.cs.wpi.edu/~claypool/mmsys-dataset/2011/affect-corpus/ Dataset can be downloaded in one ZIP file: Link: http://web.cs.wpi.edu/~claypool/mmsys-dataset/2011/affect-corpus/MMSysAffectCorpus2.zip Dataset mirror is available: http://nlp.lsu.edu/corpus/MMSysAffectCorpus2.zip Matching mp3 audio files for 119 of the stories (1 GB in total) can be downloaded from: Link: http://nlp.lsu.edu/corpus/mp3
References and Citation
Use of the datasets in published work should be acknowledged by a full citation to the paper [CK11] at the MMSys conference (MMSys 11, February 23-25, San Jose, California, USA, Copyright 2011 ACM 978-1-4503-0517-4/11/02).
CK11: R. Calix, G. Knapp, Affect Corpus 2.0: An Extension of a Corpus for Actor Level Emotion Magnitude Detection, Proceedings of the First ACM Multimedia Systems Conference (MMSys), San Jose, CA, USA, February 23-25, 2011.