SPASP 2014 - The 1st International Workshop on Sparse Representation for Audio Signal Processing (SPASP2014)

Using sparsity as a constraint in representing and analyzing audio signals has been found advantageous in various audio-related research in recent years. A sparse representation of audio signals aims at representing the information of an input signal using only a small number of elementary atoms (codewords) selected from an audio dictionary (codebook). Comparing to conventional audio features, a sparse representation is characteristic of its ability of symbolizing any local audio event as a codeword, its flexibility of using an arbitrary large number of codewords learned from a corpus of audio data in an unsupervised fashion, and its robustness to outliers, noise or corruptions in the input data. Over the past few years, sparse representations of audio signals have led to competitive performance in diverse tasks such as noise reduction, compression, speech enhancement, audio watermarking, sound and music classification, melody transcription and blind source separation, to name a few.
This workshop aims to provide a forum for the presentation of state-of-the-art research results in this emerging field and to address the growing interests in sparse representation for audio signal processing. We encourage submissions and participation to provide an opportunity for researchers from different fields to exchange ideas.
Suggested workshop topics include, but are not limited to:
Sparse coding based unsupervised or supervised audio feature learning
Sparse representation that takes into account temporal information
Sparse representation based audio classification
Sparse representation for applications in speech processing and recognition
Sparse representation for multipitich estimation or melodic transcription
Sparse representation for source separation or audio synthesis
Sparse representation for auditory modelling
Sparse representation for noise reduction
Sparse representation for audio compression
Machine learning algorithms for sparse coding
Submission should be in ISM 2014 format and maximum 6 pages. Please, consult the ISM website for the exact formatting and template. Each submission will receive at least two reviews by expert reviewers in the field in addition to a meta review by one of the organizers. Reviews will be double-blind.