New Developments in Music Signal Processing, by Meinard Müller, 09/04/2011, 2pm (+Audiosig talks)

Monday, april the 9th,  2pm.
Telecom ParisTech (Dareau)
Room: DA-006 (Vitrine de la recherche)

Author: Meinard Müller, Institut Max Planck pour l’informatique, Sarrebruck

Audiosig  also organize some talks about the research themes of the group. This is the program:

2:00 Meinard Müller, New Developments in Music Signal Processing
3:00 Romain Hennequin, Modeling of Time Variations in non-negative musical Spectrogram Decomposition
3:35 Benoit Fuentes, Multipitch Estimation: modeling continuous Variations of Pitch and spectral Enveloppe
4:10 Antoine Liutkus, Drums Separation
4:55 Manuel Moussalam, Audio Factorisation via sparse Representations
5:30 Sébastien Fenet, Audio Fingerprinting

Abstract of  Meinard Müller talk:
Compared to speech signal processing, the field of music signal processing is a relatively young research discipline. Therefore, many techniques and representations have been transferred from the speech domain to the music domain. However, music signals possess specific acoustic and structural characteristics that are not shared by spoken language or audio signals from other domains. To account for musical dimensions such as pitch or rhythm, specialized audio features that exploit musical characteristics are indispensable in analyzing and processing music data. In fact, many tasks of music signal analysis only become feasible by exploiting suitable music-specific assumptions. In this talk, I  address a number of feature design principles that account for various musical aspects. In particular, I show how chroma-based audio features can be enhanced by significantly boosting the degree of timbre invariance without degrading the features’ discriminative power. Furthermore, I introduce a novel mid-level representation that captures dominant tempo and pulse information in music recordings. To highlight the practical and musical relevance, I discuss the various feature representations in the context of current music information retrieval tasks including music synchronization, beat tracking, and structure analysis.

Comments are closed.