Search results
Enter terms
888 results found.
Section: Publications & Resources
The mission of the Information Forensics and Security Technical Committee (IFS TC) is to promote activities within the broad technical areas of information forensics and security.
Section: Publications & Resources
.
Section: Publications & Resources
The 2012 Annual Reporting and Rebate cycle has begun. All Section Officers and Chapter/Affinity Group Chairs have been contacted with a reminder that the following annual reports are required to be eligible for a rebate.
Section: Publications & Resources
The IEEE SPS congratulates the following SPS members who will receive the Society’s prestigious awards during ICASSP 2023 in Greece.
Section: Publications & Resources
Publication: IEEE Journal of Selected Topics in Signal Processing
The papers in this special section focus on self-supervised learning for speech and audio processing. A current trend in the machine learning community is the adoption of self-supervised approaches to pretrain deep networks. Self-supervised learning utilizes proxy-supervised learning tasks (or pretext tasks) - for example, distinguishing parts of the input signal from distractors or reconstructing masked input segments conditioned on unmasked segments—to obtain training data from unlabeled corpora.
Section: Publications & Resources
Publication: IEEE Journal of Selected Topics in Signal Processing
Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and languages for which only limited labeled data is available. Self-supervised representation learning methods promise a single universal model that would benefit a wide variety of tasks and domains.
Section: Publications & Resources
Publication: IEEE Journal of Selected Topics in Signal Processing
Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and languages for which only limited labeled data is available. Self-supervised representation learning methods promise a single universal model that would benefit a wide variety of tasks and domains.
