Machine Learning for Signal Processing Technical Committee
Mailing list:
Subscribe to the MLSP mailing list (do not modify or add anything to the email).
Scope of MLSP:
The Machine Learning for Signal Processing Techinical Committee (MLSP TC) is at the interface between theory and application, developing novel theoretically-inspired methodologies targeting both longstanding and emergent signal processing applications. Central to MLSP is on-line/adaptive nonlinear signal processing and data-driven learning methodologies. Since application domains provide unique problem constraints/assumptions and thus motivate and drive signal processing advances, it is only natural that MLSP research has a broad application base. MLSP thus encompasses new theoretical frameworks for statistical signal processing (e.g. machine learning-based and information-theoretic signal processing), new and emerging paradigms in statistical signal processing (e.g. independent component analysis (ICA), kernel-based methods, cognitive signal processing) and novel developments in these areas specialized to the processing of a variety of signals, including audio, speech, image, multispectral, industrial, biomedical, and genomic signals. The MLSP TC is focused on fostering research in these areas, the application of these techniques, and in educating the technical community about research developments in these areas.
The MLSP TC organizes related technical sessions at ICASSP and has an annual international workshop, now in its nineteenth year, with the above-described technical scope. In addition, MLSP has technical presence on the IEEE Transactions on Signal Processing and (currently) the IEEE Transactions on Image Processing Editorial Boards and has initiated a new set of EDICS for IEEE Transactions on Signal Processing, including a recently approved area, Cognitive Information Processing, which is emerging and expected to attract strong interest in coming years.
Recent news:
→ A discussion entitled, "Sensing Trends at ICASSP 2011: Expert Summaries of Current Trends Presented by TCs," was hosted at the ICASSP 2011 conference in Prague, Czech Republic. The MLSP Technical Committee (TC) gave three talks. Below is the overview and the links to all three presentations by the MLSP TC.
By putting the accent on “learning” from the data and the environment, the MLSP TC provides the essential bridge between the machine learning and signal processing communities. MLSP techniques have always been attractive solutions for traditional signal processing applications such as pattern recognition, speech, audio, and video processing. More importantly, owing to their polyvalent nature, these methods are also primary candidates for a new wave of emerging applications such as brain-computer interface, multimodal data fusion and processing, behavior and emotion recognition, and learning in environments such as social networks. At this session, we will discuss the role MLSP plays in such emerging applications as well as major paradigm shifts in learning as demonstrated by cognitive systems. We shall also explore what these paradigm shifts offer for the signal processing community.
May 25, 2011
Kostas Diamantaras (moderator)
Trends in Machine Learning for
Signal Processing
May 25, 2011
Tulay Adali
Current Trends in
Machine Learning for Signal Processing
May 25, 2011
Jan Larsen
Cognitive information processing
→ Two of our TC members recently gave a tutorial at ICASSP 2011 in Prague, Czech Republic. Both tutorials may be accessed below.
May 22, 2011
Jose Principe
Kernel Adaptive Filters
May 23, 2011
Paris Smaragdis
Applications of Topic Models to Speech and Audio Signal Processing: Part 1
Applications of Topic Models to Speech and Audio Signal Processing: Part 1