selected publications
-
academic article
- Greedy sparse decompositions: a comparative study. EURASIP Journal on Advances in Signal Processing. 2011. 2011
- Audio Signal Representations for Indexing in the Transform Domain. IEEE Transactions on Audio Speech and Language Processing. 18:434-446. 2010
- Explicit modeling of temporal dynamics within musical signals for acoustical unit similarity. Pattern Recognition Letters. 31:1498-1506. 2009
-
chapter
- Informed Source Separation Using Latent Components. Lecture notes in computer science. 498-505. 2010
-
conference paper
- Stochastic Gradient Richardson-Romberg Markov Chain Monte Carlo. HAL (Le Centre pour la Communication Scientifique Directe). 2016
- Multichannel audio source separation with probabilistic reverberation modeling. . 1-5. 2015
- A structured nonnegative matrix factorization for source separation. . 2033-2037. 2015
- Downbeat tracking with multiple features and deep neural networks. . 409-413. 2015
- Multipitch estimation using a PLCA-based model: Impact of partial user annotation. . 186-190. 2015
- Does Dereverberation Help Multichannel Source Separation. European Signal Processing Conference. 2013
- Does dereverberation help multichannel source separation? A case study. 1-5. 2013
- Blending real with virtual in 3DLife. . 1-4. 2013
- A probabilistic approach to simultaneous extraction of beats and downbeats. . 445-448. 2012
- Random time-frequency subdictionary design for sparse representations with greedy algorithms. . 3577-3580. 2012
- An audio-driven virtual dance-teaching assistant. Proceedings of the 30th ACM International Conference on Multimedia. 675-678. 2011
- Tutorial on multimedia music signal processing. Proceedings of the 30th ACM International Conference on Multimedia. 633-634. 2011
- AUDIO SIGNAL REPRESENTATIONS FOR FACTORIZATION IN THE SPARSE DOMAIN. . 513-516. 2011
- A conditional random field viewpoint of symbolic audio-to-score matching. Proceedings of the 30th ACM International Conference on Multimedia. 871-874. 2010
- How sparsely can a signal be approximated while keeping its class identity?. . 25-28. 2010
- Robust similarity metrics between audio signals based on asymmetrical spectral envelope matching. IEEE International Conference on Acoustics Speech and Signal Processing. 405-408. 2010