Self-Supervised Learning (SSL) of latent representations is transforming deep learning-powered technologies. In the speech and audio domains, most state-of-the-art systems rely on large Transformer neural networks pre-trained on thousands of hours of signal following various methods such as contrastive or multitask learning.

Recent top-tier conferences from the field have seen an exponential increase in the number of accepted articles mentioning self-supervised learning techniques, yet many challenges still prevent wider adoption of these techniques in real-life speech and audio technologies.

Hence, Samsung is co-organizing alongside other academic and industrial partners an official IEEE Workshop on “Self-supervision in Audio, Speech and Beyond” that will be held jointly with the IEEE International Conference on Acoustics, Speech, and Signal Processing Conference in Rhodes Island, Greece (June 2023). Hosted invited talks and keynotes combined with a dedicated submission track will deliver new insights to the world on the latest technologies revolving around self-supervised learning for audio, speech, and other modalities. Throughout a schedule that maximizes interactions within the audience via multiple panels and a poster session, the Self-supervision in Audio, Speech, and Beyond (SASB) workshop will foster interactions from the whole SSL community.

The SASB workshop accepts submissions on a broad range of topics relating to the SSL domain up until February 24th. Submitted papers will undergo a standard peer-reviewing process and accepted ones will appear in IEEE Xplore.

More information can be found at: https://sites.google.com/view/icassp-sasb-2023/description