[AUDITORY] MMSP 2017 - special session on audio processing

IEEE 19th International Workshop on Multimedia Signal Processing (MMSP)

October 16-18 2017, University of Bedfordshire (London), UK

website: https://www.beds.ac.uk/mmsp2017

Call for papers

This year's MSSP workshop will host a special session on audio, with particular focus on User Generated Content (UGC). We invite submissions in the area of UGC, encouraging innovative research methods in the area of automatic organization of UGC, with focus on automatical discovery, matching, grouping and synchronization of overlapping audio (or video) files of the same event.

Additionally, we invite complete or visionary papers in the area of collaborative processing of UG audio recordings, where, given a collection of overlapping UG audio streams, the articles propose strategies for combining the available content with the goal to improve the overall acoustic representation of the captured event.

Some possible topics along these directions are:

- Automatic UGC organization

- Multi-microphone sound scene analysis

- Mixing of geographically spread UG audio recordings

- Multichannel sound reproduction based on UGC

- Sound source/scene enhancement and source/scene separation

- Foreground suppression and privacy preservation

- Combination of UGC with professional content

To support potential contributions in these topics, we provide two open-access audio datasets with user generated audio recordings in PCM format. In particular, we visited and captured parts of a musical performance and parts of a crowded football match, and the audio files are available at https://doi.org/10.5281/zenodo.164175 while in an accompanying paper (https://doi.org/10.5281/zenodo.167311) we describe how the recordings were generated in each event. Specifically, to facilitate the different research directions, we provide the content in two different forms:

As an unorganized collection, where the available audio streams are stored in a single folder and each audio file preserves its original duration and channel format (mono or stereo)
As an organized collection, where the audio files are matched and grouped into specific folders, and moreover, a silent region of proper duration is added at the beginning of each audio file so that all files in the same folder are synchronized with one another.

In addition to the above UGC-related topics, submissions on established multi-microphone signal processing areas are also encouraged, including but not limited to:

- Ad-hoc microphones and microphone arrays

- Wireless Acoustic Sensor Networks (WASNs)

- Multi-microphone processing for spatial audio and immersive sound reproduction

The deadline for the paper submission is on 1st of June 2017.

Further details related to the particular special session will be available at

https://www.beds.ac.uk/mmsp2017/special-session-proposals

For any questions related to the event, please get in touch with us in the following addresses:

Nikos Stefanakis (nstefana@xxxxxxxxxxxx)
Athanasios Mouchtaris (mouchtar@xxxxxxxxxxxx)

Paris Smaragdis (paris@xxxxxxxxxxxx)