I obtained my PhD in Electrical Engineering from the University of Minnesota in October 2012. My adviser was Guillermo Sapiro. During 2013 I worked as a Postdoctoral researcher at the IID (Information initiative at Duke) at Duke University.
My main research interests are in machine learning and it's applications to computer vision, and signal processing. Specifically,
Sparse modeling and representation learning from high dimensional data.
Source separation, speech processing, and music information retreival.
Here you can find my CV.
List of publications by Google Scholar and
selected works by area:
J, Bruna, P. Sprechmann, and Y. LeCun, “Super-Resolution with Deep Convolutional Sufficient Statistics,” in arxiv (ICLR), 2016.
P. Sprechmann, A. M. Bronstein, and G. Sapiro, “Learning efficient sparse and low rank models,” in IEEE TPAMI, 2015.
J. Masci, A. M. Bronstein, M. M. Bronstein, P. Sprechmann, and G. Sapiro, “Sparse similarity-preserving hashing,” (ICLR), 2014. (Oral presentation).
P. Sprechmann, R. Litman, T. B. Yakar, A. M. Bronstein, and G. Sapiro, “Supervised sparse analysis and synthesis operators,” (NIPS), 2013.
P. Sprechmann, A. M. Bronstein, and G. Sapiro, “Learning Efficient Structured Sparse Models,” (ICML), 2012. (Oral presentation).
P. Sprechmann, I. Ramirez, G. Sapiro, and Y. C. Eldar, “C-HiLasso: A collaborative hierarchical sparse modeling framework,” IEEE TSP, 2011.
P. Sprechmann, J. Bruna, Y.LeCun, ’'Audio Source Separation with Discriminative Scattering Networks’’, (LVA/ICA), 2015. (Invited paper).
J. Bruna, P. Sprechmann, and Y. LeCun, ’'Source separation with scattering non-negative matrix factorization’’, (ICASSP), 2014.
P. Sprechmann, A. M. Bronstein, and G. Sapiro, “Supervised non-Euclidean sparse NMF via bilevel optimization with applications to speech enhancement,” (HSCMA), 2014. (Invited paper).
P. Sprechmann, A. M. Bronstein, M. M. Bronstein, and G. Sapirom “Learnable low rank sparse models for speech denoising,” (ICASSP), 2013.
T. B. Yakar, P. Sprechmann, R. Litman, A. M. Bronstein, and G. Sapiro, “Bilevel sparse models for polyphonic music transcription.,” (ISMIR), 2013.
P. Sprechmann, A. M. Bronstein, and G. Sapiro, “Real-time online singing voice separation from monaural recordings using robust low-rank modeling,” (ISMIR), 2012. (Best poster presentation award)
P. Sprechmann, P. Cancela, and G. Sapiro, “Gaussian mixture models for score-informed instrument separation,” (ICASSP), 2012.
P. Sprechmann, I. Ramirez, P. Cancela, and G. Sapiro, “Collaborative sources identification in mixed signals via hierarchical sparse modeling,” (ICASSP), 2011.
M. Tepper, A. Newson, P. Sprechmann, and G. Sapiro. ’'Multi-temporal foreground detection in videos.’’, (ICIP), 2015 (source code and examples).
I. Ramirez, P. Sprechmann, and G. Sapiro, “Classification and clustering via dictionary learning with structured incoherence,” (CVPR), 2010. (Oral presentation).
M. Fiori, P. Sprechmann, J. Vogelstein, P. Muse, and G. Sapiro, “Robust multimodal graph matching: sparse coding meets graph matching,” (NIPS), 2013. (Spotlight presentation).
J. Pokrass, A. M. Bronstein, M. M. Bronstein, P. Sprechmann, and G. Sapiro, “Sparse modelling of intrinsic correspondences,” in (Eurographics), 2013.
K. Carpenter, P. Sprechmann, M. Fiori, R. Calderbank, H. Egger, and G. Sapiro, “Questionnaire simplification for fast risk analysis of children mental health,” (ICASSP), 2014.
C. Aguerrebere, P. Sprechmann, P. Muse, and R. Ferrando, “A-contrario localization of epileptogenic zones in SPECT images,” (ISBI)., 2009.
A. Bartesaghi, P. Sprechmann, J. Liu, G. Randall, G. Sapiro, and S. Subramaniam, “Classification and 3D averaging with missing wedge correction in biological electron tomography,” Journal of Structural Biology , 2008.
P. Arias, A. Pini, G. Sanguinetti, P. Sprechmann, P. Cancela, A. Fernandez, A. Gomez, and G. Randall, “Ultrasound image segmentation with shape priors: application to automatic cattle rib-eye area estimation,” IEEE TIP, 2007.
“Deep learning for solving inverse problems”, Speech and Audio in the Northeast workshop (SANE) held at Google New York, October 2015 (Oral).
“Multi-level structured sparse models”, Workshop on Computational Harmonic Analysis, Image and Signal Processing, Foundations of Computational Mathematics (FoCM), December 2014 (Oral).
“Sparse similarity-preserving hashing”, Sensing and Analysis of High-Dimensional Data, Duke University. July 2013. (Poster)
“Learning to optimize”, at the Adaptive Data Analysis and Sparsity workshop at the Institute for Pure and Applied Mathematics (IPAM), UCLA. January 2013. (Oral)
“Sparse similarity-preserving hashing”, Duke Workshop on Sensing and Analysis of High-Dimensional Data (SAHD), July 2013. (Poster)
“Audio source modeling based on structured sparsity and GMM using temporal constraints”, Duke Workshop on Sensing and Analysis of High-Dimensional Data (SAHD), July 2011. (Poster)
“Collaborative source separation and identification in images and signals via hierarchical sparse modeling”, at the Workshop: Trends in Mathematical Imaging and Surface Processing, Mathematisches Forschungsinstitut Oberwolfach, Oberwolfach, Germany, January 2011. (Oral)