Publications - Paris Smaragdis

2021

Tzinis, E., J. Casebeer, Z. Wang, P. Smaragdis. Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data, in proceedings of IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, Mohonk Mountain House, New Paltz, NY, 2021. [PDF]
Subramani, K. and P, Smaragdis. Point Cloud Audio Processing, in proceedings of IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, Mohonk Mountain House, New Paltz, NY, 2021 Best Paper Award. [PDF]
Casebeer, J., N. Bryan, P. Smaragdis. Auto-DSP: Learning to Optimize Acoustic Echo Cancellers, in proceedings of IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, Mohonk Mountain House, New Paltz, NY, 2021. [PDF]
Wang, Z., J. Casebeer, A. Clemmitt, E. Tzinis, P. Smaragdis, Sound Event Detection with Adaptive Frequency Selection, in proceedings of IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, Mohonk Mountain House, New Paltz, NY, 2021. [PDF]
Ramírez, M., O. Wang, P. Smaragdis, N. J. Bryan. Differentiable Signal Processing With Black-Box Audio Effects, in IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Toronto, Canada, 2021. [PDF]
Zhao, A., K. Subramani, P. Smaragdis. Optimizing Short-Time Fourier Transform Parameters via Gradient Descent, In IEEE International Conference on Acoustics, Speech, and Signal Pro- cessing (ICASSP), Toronto, Canada, 2021. [PDF]
Tzinis, E., D. Bralios, P. Smaragdis. Unified Gradient Reweighting For Model Biasing with Applications to Source Separation, in IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Toronto, Canada, 2021. [PDF]
Casebeer, J., J. Kaikaus, P. Smaragdis. Communication-Cost Aware Microphone Selection for Neural Speech Enhancement with Ad-Hoc Microphone Arrays, in IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Toronto, Canada, 2021. [PDF]

2020

Tzinis, E., Z. Wang and P. Smaragdis. Sudo rm-rf: Efficient Networks for Universal Audio Source Separation, in IEEE Workshop on Machine Learning for Signal Processing, September 2020. [PDF]
Mimilakis, S., N. Bryan, and P. Smaragdis. One-Shot Parametric Audio Production Style Transfer with Application to Frequency Equalization. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, Spain, 2020. [PDF]
Venkataramani, S., E. Tzinis, and P. Smaragdis. End-to-end Non-Negative Autoencoders for Sound Source Separation. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, Spain, 2020. [PDF]
Tzinis, E., S. Venkataramani, Z. Wang, Y.C. Sübakan and P. Smaragdis. Two-Step Sound Source Separation: Training on Learned Latent Targets. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, Spain, 2020. [PDF]

2019

P. Seetharaman, G. Mysore, B. Pardo, P. Smaragdis, and C. Gomes. VoiceAssist: Guiding Users to High-Quality Voice Recordings, in ACM CHI Conference on Human Factors in Computing Systems, May 2019, Glascow UK. [PDF]

D. Fagot, H. Wendt, C. Fevotte, and P. Smaragdis. Majorization-Minimization Algorithms for Convolutive NMF with the Beta-Divergence, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2019, Brighton, UK. [PDF]
J. Casebeer, Z. Wang, and P. Smaragdis. Multi-View Networks for Multi-Channel Audio Classification, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2019, Brighton, UK. [PDF]
E. Tzinis, S. Venkataramani, and P. Smaragdis. Usupervised Deep Clustering for Source Separation: Direct Learning from Mixtures Using Spatial Information, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2019, Brighton, UK. [PDF]

2018

Venkataramani, S., R. Higa, and P. Smaragdis. Performance Based Cost Functions for End-to-End Speech Separation. APSIPA Annual Summit and Conference 2018, November 2018, Hawaii [PDF]
Casebeer, J., B. Luc, and P. Smaragdis. Multi-View Networks for Denoising of Arbitrary Numbers of Channels, in IEEE International Workshop on Acoustic Signal Enhancement, September, Tokyo, Japan. [PDF]
Venkataramani, S., J. Casebeer, and P. Smaragdis. End-to-end Source Separation with Adaptive Front-Ends, in IEEE Asilomar Conference on Signals, Systems, and Computers, Pacific Grove CA, USA. [PDF]
Sübakan, C.Y., and P. Smaragdis. Generative Adversarial Source Separation, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, Canada, 2018 [PDF]
Kim, M. and P. Smaragdis. Bitwise Neural Networks for Efficient Single-Channel Source Separation, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, Canada, 2018 [PDF]
Seetharaman, P., G.J. Mysore, P. Smaragdis, B. Pardo, Blind Estimation of the speech transmission index for speech quality prediction, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, Canada, 2018 [PDF]

2017

Kim, M. and P. Smaragdis. Bitwise Neural Networks for Efficient Single-Channel Source Separation, in Workshop for Audio Signal Processing, NIPS 2017 [PDF]
Venkataramani, S., J. Casebeer, and P. Smaragdis. Adaptive Front-ends for End-to-end Source Separation, in Workshop for Audio Signal Processing, NIPS 2017 [PDF]
Sübakan, Y.C. and P. Smaragdis. 2017. Diagonal RNNs in Symbolic Music Modeling, in IEEE Workshop for Applications of Signal Processing to Audio and Acoustics (WASPAA), New Paltz, NY, USA. October 2017 [PDF]
Correa Carvalho, R.G., and P. Smaragdis. 2017. Towards End-to-end Polyphonic Music Transcription: Transforming Music Audio Directly to a Score, in IEEE Workshop for Applications of Signal Processing to Audio and Acoustics (WASPAA), New Paltz, NY, USA. October 2017. [PDF]
Venkataramani, S., P. Smaragdis, G. Mysore. 2017. AutoDub: Automatic Redubbing for Voiceover Editing, in ACM User Interface Software and Technology (UIST), in Quebec City, Canada, October 2017. [PDF]
Venkataramani, S., Y.C. Sübakan, and P. Smaragdis. 2017. A Neural Network Alternative to Convolutive Audio Models For Source Separation. 2017. In IEEE Workshop on Machine Learning for Signal Processing (MLSP), Tokyo, Japan, September. 2017.[PDF]
Fevotte, C., G. Mysore, P. Smaragdis, and N. Mohammadiha. 2017. Temporal extensions of Nonnegative Matrix Factorization, in Audio Source Separation and Speech Enhancement, eds. E. Vincent, T. Virtanen, S. Gannot. Wiley.
Smaragdis, P., G. Mysore, and N. Mohammadiha. 2017. Temporal NMF models: HMMs with NMF and Kalman filters, ed. Shoji Makino, Springer.
Minje, K. and P. Smaragdis. 2017. Efficient Source Separation Using Bitwise Neural Networks, in Audio Source Separation, ed. Shoji Makino, Springer.
Smaragdis, P. and S. Venkataramani. 2017. A Neural Network alternative to Non-Negative Audio Models, in proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, New Orleans, LA. 2017. [PDF]

2016

Babaeizadeh, M., P. Smaragdis R.H. Campbell. 2016. International Workshop on Efficient Methods for Deep Neural Networks, Barcelona, Spain. [PDF]
Friedlander, G., P. Smaragdis, B. Raj, and J. McDermott. 2016. Audition for Multimedia Computing, in ACM Book on Research Frontiers of Multimedia, ed. Shi-Fu Chang. Morgan-Claypool.
Traa, J., D. Wingate, N. Stein, and P. Smaragdis. 2016. Robust Source Localization and Enhancement With a Probabilistic Steered Response Power Model. In IEEE Transactions of Audio Speech and Language Processing. [PDF]
Kim, M. and P. Smaragdis. 2016. Efficient Neighborhood-Based Topic Modeling For Collaborative Audio Enhancement On Massive Crowdsourced Recordings. in IEEE International Conference on Acoustics, Speech, and Signal Processing (pP), Shanghai, China, 2016. [PDF]

2015

Huang, P.-S., M. Kim, M. Hasegawa-Johnson, P. Smaragdis. 2015. Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation. In IEEE Transactions of Audio Speech and Language Processing, to appear [PDF]
Traa, J., P. Smaragdis, N. Stein, D. Wingate. 2015. Directional NMF for Joint Source Separation and Localization. In proceedings of IEEE workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA). New Paltz, NY. October 2015 [PDF]
S端bakan, Y.C., J. Traa, P. Smaragdis, D. Hsu. 2015. Method of Moments Learning for Left to Right Hidden Markov Models, In proceedings of IEEE workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA). New Paltz, NY. October 2015 [PDF]
Kim, M. and P. Smaragdis. 2015. Adaptive Denoising Autoencoders: A Fine-tuning Scheme to Learn from Test Mixtures, in 12th International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA 2015), Liberec, Czech Republic, August 2015 [PDF]
Kim, M. and P. Smaragdis. 2015. Bitwise Neural Networks, in ICML2015 Workshop on Resource-Efficient Machine Learning, Lille France, July 2015 [PDF]
Aki Nikolaidis, Drew Goatz, Paris Smaragdis and Arthur Kramer. 2015. Predicting Skill-Based Task Performance and Learning with fMRI Motor and Subcortical Network Connectivity, in 5th International Workshop on Pattern Recognition in Neuroimaging, Stanford University, June 10-12 2015. [PDF
Virtanen, T., J. Gemmeke, B. Raj and P. Smaragdis. 2015. Compositional models for audio processing, in IEEE Signal Processing Magazine, March 2015. [PDF]
Mohammadiha, N. P. Smaragdis and S. Doclo. 2015. Joint Acoustic and Spectral Modeling for Speech Dereverberation using Non-Negative Representations, in IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Brisbane, Australia, April 19-24, 2015. [PDF]
Kim, M., P. Smaragdis, and G.J. Mysore. 2015, Efficient Manifold Preserving Audio Source Separation Using Locality Sensitive Hashing, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Brisbane, Australia, April 19-24, 2015. [PDF]
Kim, M. and P. Smaragdis. 2015. Mixtures of Local Dictionaries for Unsupervised Speech Enhancement, in IEEE Signal Processing Letters, Vol. 22, No. 3, pp. 288-292, Mar. 2015. [PDF]

2014

Mohammadiha, N., P. Smaragdis, G. Panahandeh and S. Doclo. 2015, A State-Space Approach to Dynamic Nonnegative Matrix Factorization, in IEEE Transactions on Signal Processing, to appear. [PDF]
Kim, M., and P. Smaragdis. 2014. Collaborative Audio Enhancement: Crowdsourced Audio Recording, in Neural Information Processing Systems (NIPS) 2014, Workshop on CrowdSourcing and Machine Learning. Montreal, Canada. [PDF]
Sübakan, Y.C., J. Traa and P. Smaragdis. 2014. Spectral Learning of Mixture of Hidden Markov Models, in Neural Information Processing Systems (NIPS) 2014. Montreal, Canada. [PDF]
Traa, J. and P. Smaragdis. 2014. Multichannel Source Separation and tracking with RANSAC and Directional Statistics, in IEEE Transactions on Audio, Speech and Language Processing, to appear. [PDF]
Kim, M. and P. Smaragdis. 2014. Efficient Model Selection for Speech Enhancement Using a Deflation Method for Nonnegative Matrix Factorization, in GlobalSIP 2014, accepted. [PDF]
Kim, M. and P. Smaragdis. 2014. Mixtures of Local Dictionaries for Unsupervised Speech Enhancement, in Signal Processing Letters, accepted. [PDF]
Huang P.-S., M .Kim, M. Hasegawa-Johnson, and P. Smaragdis. 2014. Singing-Voice Separation from Monaural Recordings Using Deep Recurrent Neural Networks, in International Symposium of Music Information Retrieval, Taipei, Taiwan. [PDF]
Traa, J. and P. Smaragdis. 2014. Multiple Speaker Tracking with the Factorial von Mises-Fisher Filter, in Proceedings of the IEEE Machine Learning for Signal Processing Workshop, Reims, France, Sept. 2014 [PDF]
Liu, D., P. Smaragdis, M. Kim. 2014. Experiments on Deep Learning for Speech Denoising, in Proceedings of the annual conference of the International Speech Communication Association (INTERSPEECH), Singapore. 2014 [PDF]
Huang, P-S., M. Kim, M. Hasegawa-Johnson, P. Smaragdis. 2014. Deep Learning for Monaural Speech Separation, in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Florence, Italy. 2014 [PDF]
Smaragdis, P., C. Fevotte, G. Mysore, N. Mohammadiha, M. Hoffman 2014. Static and Dynamic Source Separation Using Nonnegative Factorizations: A unified view, in IEEE Signal Processing Magazine May 2014 [PDF]
Virtanen, T., J. Gemmeke, B. Raj and P. Smaragdis. 2014. Compositional models for audio processing, in IEEE Signal Processing Magazine, accepted [PDF]

2013

Traa, J. and P. Smaragdis. 2013. A Wrapped Kalman Filter for Azimuthal Speaker Tracking, IEEE Signal Processing Letters, to appear [PDF]
Mohammadiha, N., P. Smaragdis, A. Leijon. 2013. Supervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization, in IEEE Transactions on Audio, Speech and Language Processing, to appear [PDF] [ MATLAB Code]
Mohammadiha, N., P. Smaragdis, A. Leijon. 2013. Low-Artifact Source Separation using Probabilistic Latent Component Analysis, in IEEE Workshop for Applications of Signal Processing in Audio and Acoustics. New Paltz, NY. October 2013. [PDF]
Smaragdis, P. and M. Kim. 2013. Non-Negative Matrix Factorization for Irregularly-Spaced Transforms, in IEEE Workshop for Applications of Signal Processing in Audio and Acoustics. New Paltz, NY. October 2013. [PDF]
Mohammadiha, N., P. Smaragdis, A. Leijon. 2013. Simultaneous Noise Classification and Reduction using a Priori Learned Models, in IEEE Workshop for Machine Learning in Signal Processing, Southampton, UK. September 2013. [PDF]
Kim, M. and P. Smaragdis. 2013. Single Channel Source Separation Using Smooth Nonnegative Matrix Factorization with Markov Random Fields, in IEEE Workshop for Machine Learning in Signal Processing, Southampton, UK. September 2013. [PDF]
Kim, M. and P. Smaragdis. 2013. Manifold Preserving Hierarchical Topic Models for Quantization and Approximation, in International Conference on Machine Learning, Atlanta, GA. June 2013. [PDF]
Kim, M. and P. Smaragdis. 2013. Collaborative Audio Enhancement Using Probabilistic Latent Component Sharing, in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, Canada. 2013. [PDF]
Traa, J. and P. Smaragdis. 2013. Blind Multi-Channel Source Separation by Circular-Linear Statistical Modeling of Phase Differences, in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, Canada. 2013. [PDF]
Mohammadiha, N., P. Smaragdis and A. Leijon. 2013. Prediction Based Filtering and Smoothing to Exploit Temporal Dependencies in NMF, in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, Canada. 2013. [PDF]
Pathak, M.A., B. Raj, S. Rane, P. Smaragdis. 2013. Privacy Preserving Speech Processing, in IEEE Signal Processing Magazine, February 2013 [Draft PDF][Final PDF]
Zhang, C., G.G. Ko, J.W. Choi, S.-N. Tsai, M. Kim, A.G. Rivera, R. Rutenbar, P. Smaragdis, M.S. Park, V. Narayanan, H. Xin, O. Mutlu , B. Li, L. Zhao, M. Chen, R. Iyer. 2013. EMERALD: Characterization of Emerging Applications and Algorithms for Low-power Devices, 2013 IEEE International Symposium on Performance Analysis of Systems and Software, April 21-23, 2013, Austin, TX

2012

Smaragdis, P. 2012. Extraction of Speech from Mixture Signals, book chapter in Techniques for Noise Robustness in Automatic Speech Recognition, T. Virtanen, R. Singh, B. Raj (eds). Wiley. [Book link]
King, B., C. Févotte, and P. Smaragdis. 2012. Optimal Cost and Magnitude Power for nmf-Based Speech Separation and Music Interpolation, in Proceedings of the 2012 ieee International Workshop on Machine Learning for Signal Processing, Sept. 23-26, 2012, Satander, Spain.[PDF]
Kim., M., P. Smaragdis, G.G. Ko, R.A. Rutenbar. 2012. Stereophonic Spectrogram Segmentation Using Markov Random Fields, in Proceedings of the 2012 ieee International Workshop on Machine Learning for Signal Processing, Sept. 23-26, 2012, Satander, Spain. [PDF]
Bay, M., A.F. Ehmann, J.W. Beauchamp, P. Smaragdis, J.S. Downie. 2012. Second Fiddle is Important Too: Pitch Tracking Individual Voices in Polyphonic Music, in Proceedings of the 13th International Society for Music Information Retrieval Conference, Porto, Portugal. October 2012. [PDF]
Duan, Z., G.J. Mysore, P. Smaragdis. 2012. Speech Enhancement by Online Non-Negative Spectrogram Decomposition in Non-Stationary Noise Environments, in Proceedings of the 13th Annual COnference of the International Speech Communication Association (INTERSPEECH), Portland, OR, USA. September 2012. [PDF]
Nielsen, J.K., P. Smaragdis, M.G. Christensen, S.H. Jensen. 2012. An Amplitude Spectral Capon Estimator with a Variable Filter Length, in Proceedings of the 20th European Signal Processing Conference (EUSIPCO), Bucharest, Romania. August 2012. [PDF]
Smaragdis, P. G.J. Mysore. 2012. Following Musical Sources by Example, in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Kyoto, Japan. March 2012. [PDF] Invited Paper
Bryan, N.J., P. Smaragdis, G.J. Mysore. 2012. Clustering and Synchronizing Multi-Camera Video via Landmark Cross-Correlation, in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Kyoto, Japan. March 2012. [PDF]
King, B., P. Smaragdis, G.J. Mysore. 2012. Noise-Robust Dynamic Time Warping using PLCA Features, in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Kyoto, Japan. March 2012. [PDF]
Huang, P-S. S.D. Chen, P. Smaragdis, M. Hasegawa-Johnson. 2012. Singing-Voice Separation from Monaural Recordings Using Robust Principal Component Analysis, in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Kyoto, Japan. March 2012. [PDF]
Nam, J., G.J. Mysore, and P. Smaragdis, 2012. Sound Recognition in Mixtures, in the proceedings of the international conference on Latent Variable Analysis / Independent Component Analysis, Tel-Aviv, Israel, 2012 [PDF]
Mysore, G.J. and P. Smaragdis. 2012. A Non-negative Approach to Language Informed Speech Separation, in the proceedings of the international conference on Latent Variable Analysis / Independent Component Analysis, Tel-Aviv, Israel, 2012 [PDF]
Duan, Z., G.J. Mysore and P. Smaragdis. 2012. Online PLCA for Real-time Semi-supervised Source Separation, in the proceedings of the international conference on Latent Variable Analysis / Independent Component Analysis, Tel-Aviv, Israel, 2012 [PDF]

2011

Boufounos, P., P. Smaragdis and B. Raj. 2011 Joint sparsity models for wideband array processing, in Proceedings of the international society for optics and photonics (SPIE) 8138. [PDF]
Smaragdis, P., B. Raj. 2011. The Markov Selection Model for Concurrent Speech Recognition. Neurocomputing Journal, [PDF] Invited Paper
Smaragdis, P. 2011. Polyphonic pitch tracking by example. In proceedings of IEEE Workshop on Applications Signal Processing to Audio and Acoustics. New Paltz, NY, USA. October 2011 [PDF]
Mysore G., and P. Smaragdis. 2011. A convolutive spectral decomposition approach to the separation of feedback from target speech. In proceedings IEEE international workshop on Machine Learning for Signal Processing (MLSP). Beijing, China. September 2011 [PDF]
Smaragdis, P. 2011. Approximate nearest-subspace representations for sound mixtures. In Proceedings Interntational Conference on Acoustics, Speech and Signal Processing (ICASSP). Prague, Czech Republic, May, 2011 [PDF]
Mysore, G. and P. Smaragdis. 2011. A non-negative approach to semi-supervised separation of speech from noise with the use of temporal dynamics. In Proceedings Interntational Conference on Acoustics, Speech and Signal Processing (ICASSP). Prague, Czech Republic, May, 2011 [PDF]
Kirbiz S. and P. Smaragdis. 2011. An adaptive time-frequency resolution approach for non-negative matrix factorization based single channel source separation. In Proceedings Interntational Conference on Acoustics, Speech and Signal Processing (ICASSP). Prague, Czech Republic, May, 2011 [PDF]

2010

Mysore, G., P. Smaragdis, and B. Raj. 2010. Non-negative hidden Markov modeling of audio with application to source separation. In 9th international conference on Latent Variable Analysis and Signal Separation (LCA/ICA). St. Malo, France. September, 2010 [PDF] Best paper award
Brown, J.C., P. Smaragdis, and A. Nousek-McGregor. 2010. Automatic identification of individual killer whales, in the Journal of the Acoustical Society of America 128 (3), Express Letters. September 2010. [PDF]
Smaragdis, P., B. Raj, M. Shashanka. 2010. Missing data imputation for time-frequency representations of audio signals, in the Journal of Signal Processing Systems. August 2010. [PDF]
Smaragdis, P. and B. Raj. 2010. The Markov selection model for concurrent speech recognition. In IEEE international workshop on Machine Learning for Signal Processing (MLSP). August 2010, Kittilä, Finland. [PDF]
Singh, R., B. Raj and P. Smaragdis. 2010. Latent-variable decomposition based dereverberation of monaural and multi-channel signals, in proceedings IEEE International Conference on Audio and Speech Signal Processing, Dallas, TX, USA March 2010. [PDF]

2009

Smaragdis, P., M. Shashanka, and B. Raj. 2009. A sparse non-parametric approach for single channel separation of known sounds. In Neural Information Processing Systems. Vancouver, BC, Canada. December 2009. [PDF]
Smaragdis, P. and G. Mysore. 2009. Separation by “humming”: User-guided sound extraction from monophonic mixtures. In proceedings of IEEE Workshop on Applications Signal Processing to Audio and Acoustics. New Paltz, NY. October 2009. [PDF]
Smaragdis, P. 2009. User guided audio selection from complex sound mixtures. in the 22nd ACM Symposium on User Interface Software and Technology (UIST 09). Victoria, BC, Canada, October 2009. [PDF] [Demo Video]
Smaragdis, P., B. Raj, M. Shashanka. 2009. Missing data imputation for spectral audio signals, in IEEE international workshop on Machine Learning for Signal Processing (MLSP). September 2009, Grenoble, France. [PDF]
Smaragdis, P. 2009. Dynamic Range Extension using Interleaved Gains, in IEEE Transactions of Audio, Speech and Language Processing, July 2009. [PDF]
Brown J. and P. Smaragdis. 2009. Hidden Markov and Gaussian mixture models for automatic call classification. In Journal of the Acoustical Society of America Express Letters. May 2009. [PDF]
Smaragdis, P. 2009. Relative Pitch Tracking of Multiple Arbitrary Sounds. In Journal of the Acoustical Society of America, Volume 125, Issue 5, pp. 3406-3413 (May 2009) [PDF]
Smaragdis, P. 2009. Dynamic Range Extension using Interleaved Gains, in IEEE Transactions of Audio, Speech and Language Processing, vol. 7(5), July 2009. [PDF]
Nakra, T., Y. Ivanov, P. Smaragdis and C. Ault. 2009. The UBS Virtual Maestro: an Interactive Conducting System. In proceedings of New Interfaces for Musical Expression 2009 conference. Pittsburgh, PA USA. June 2009. [PDF]
Mysore, G. and P. Smaragdis, 2009. Relative Pitch Estimation of Multiple Instruments, In proceedings IEEE International Conference on Audio and Speech Signal Processing, Taipei, Taiwan, USA. April 2009. [PDF]
Smaragdis, P., M. Shashanka, B. Raj and G. Mysore. 2009. Probabilistic Factorization of Non-Negative Data with Entropic Co-occurrence Constraints. In proceedings 8th International Conference on Independent Component Analysis and Signal Separation (ICA 2009). Paraty, Brazil, March 2009. [PDF]

2008

Wilson, K.W., B. Raj, and P. Smaragdis, 2008. Regularized Non-Negative Matrix Factorization with Temporal Dependencies for Speech Denoising. In proceedings of Interspeech 2008, Brisbane, Australia, September 2008. [PDF]
Shashanka, M.V., B. Raj and P. Smaragdis, 2008. Probabilistic Latent Variable Models as Non-Negative Factorizations. In special issue on Advances in Non-negative Matrix and Tensor Factorization, Computational Intelligence and Neuroscience Journal. May 2008. [PDF]
Smaragdis, P, B. Raj, and M.V. Shashanka, 2008. Sparse and shift-invariant feature extraction from non-negative data. In proceedings IEEE International Conference on Audio and Speech Signal Processing, Las Vegas, Nevada, USA. April 2008. [PDF]
Wilson, K., B. Raj, P. Smaragdis, A. Divakaran. 2008. Speech denoising using non-negative matrix factorization with priors.In proceedings IEEE International Conference on Audio and Speech Signal Processing, Las Vegas, Nevada, USA. April 2008. [PDF]

2007

Shashanka, M.V., B. Raj, P. Smaragdis, 2007. Sparse Overcomplete Latent Variable Decoposition of Counts Data. In Neural Information Processing Systems (NIPS), Vancouver, BC, Canada. December 2007.[PDF], [Supplement]
Smaragdis, P. and B. Raj. 2007. Example-driven bandwidth expansion. In proceedings of IEEE workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA). New Paltz, NY. October 2007. [PDF]
Shashanka, M. and P. Smaragdis. 2007. Privacy-preserving musical database matching. In proceedings of IEEE workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA). New Paltz, NY. October 2007. [PDF]
Smaragdis, P. and Raj, B. 2007. Shift-Invariant Probabilistic Latent Component Analysis, tech report [PDF] [MATLAB Code]
Smaragdis, P. and Raj, B. 2007. Audio-assisted cameras and acoustic doppler sensors, in "Multimodal Surveillance: Sensors, Algorithms and Systems", Zhigang Zhu, Tom Huang (eds), Artech House. [Book Link]
Smaragdis, P. 2007. Component based techniques for monophonic speech separation and recognition, in "Blind Speech Separation", S. Makino, T-W.Lee and H. Sawada (eds.) Blind Speech Separation, Springer. [Book Link]
Smaragdis, P. Raj, B. and Shashanka, M.V. 2007. Supervised and Semi-Supervised Separation of Sounds from Single-Channel Mixtures. In proceedings of the 7th International Conference on Independent Component Analysis and Signal Separation. London, UK. September 2007. [PDF]
Smaragdis, P. and Shashanka, M.V. 2007. A Framework for Secure Speech Recognition. In IEEE Transactions on Audio, Speech and Language Processing. May 2007. [PDF]
Shashanka, M.V., Raj, B., Smaragdis, P. 2007. Sparse Overcomplete Decomposition for Single Channel Speaker Separation. In proceedings IEEE International Conference on Audio and Speech Signal Processing, Honolulu, Hawaii, USA. 15-20 April 2007. [PDF]
Smaragdis, P., and Shashanka, M.V. 2007. A Framework for Secure Speech Recognition. In proceedings IEEE International Conference on Audio and Speech Signal Processing, Honolulu, Hawaii, USA. 15-20 April 2007. [PDF]
Raj, B., Singh, R., Shashanka, M.V., Smaragdis, P. 2007. Bandwidth expansion with a Polya urn model. In proceedings IEEE International Conference on Audio and Speech Signal Processing, Honolulu, Hawaii, USA. 15-20 April 2007. [PDF]
Smaragdis, P.; Boufounos, P. 2007. Position and Trajectory Learning for Microphone Arrays, In IEEE Transactions on Speech and Audio Processing. January 2007. [PDF]
Smaragdis, P. 2007. Convolutive Speech Bases and their Application to Speech Separation. In IEEE Transactions of Speech and Audio Processing. January 2007. [PDF]
Raj, B., Smaragdis, P., Shashanka, M.V. and Singh, R. 2007, Separating a foreground singer from background music. In proceedings, International Symposium on Frontiers of Research on Speech and Music (FRSM) Jan. 2007, Mysore, India. [PDF]

2006

Smaragdis, P., Raj, B. and Shashanka, M.V. 2006, A probabilistic latent variable model for acoustic modeling, Advances in models for acoustic processing workshop, NIPS 2006. [PDF] [PPT]
Shashanka, M.V.; Smaragdis P. 2006. Secure Sound Classification: Gaussian Mixture Models. In Proceedings ICASSP 2006. Toulouse, France, May 2006. [PDF]
Smaragdis, P.; Shashanka, M.V.; Raj, B. 2006. Latent Dirichlet Decomposition for Single Channel Speaker Separation. In Proceedings ICASSP 2006. Toulouse, France, May, 2006. [PDF]

2005

Smaragdis, P.; Boufounos, P. 2005. Learning Source Trajectories using Wrapped-Phase Hidden Markov Models. In Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, New Paltz, NY, October, 2005. [PDF]
Radhakrishnan, R.; Divakaran, A.; Smaragdis, P. 2005. Audio Analysis for Surveillance Applications, In Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, New Paltz, NY, October, 2005. [PDF]
Raj, B.; Smaragdis, P. 2005. Latent Variable Decomposition of Spectrograms for single channel speaker separation. In Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, New Paltz, NY, October, 2005. [PDF]
Bansal, D.; Raj, B.; Smaragdis, P. 2005. Bandwidth Expansion of Narrowband Speech using Non-Negative Matrix Factorization. In Proceedings of EUROSPEECH 2005, Lisbon, Portugal, September 2005. [PDF]
Raj, B.; Singh, R.; Smaragdis, P. 2005. Recognizing Speech from Simultaneous Speakers. In Proceedings of EUROSPEECH 2005, Lisbon, Portugal, September 2005. [PDF]
Smaragdis, P. 2005. From Learning Music to Learning to Separate. Invited paper at Forum Acusticum 2005, Budapest, Hungary, August 2005. [PDF]
Radhakrishnan, R.; Divakaran, A.; Smaragdis, P., 2005. Systematic Acquisition of Audio Classes for Elevator Surveillance, SPIE Image and Video Communications and Processing , Vol. 5685, pp. 64-71, March 2005. [PDF]

2004

Smaragdis, P. 2004. Discovering Auditory Objects through Non-Negativity Constraints. In ISCA Tutorial and Research Workshop on Statistical and Perceptual Audio Processing, Jeju, South Korea, October 2004. [PDF]
Smaragdis, P. 2004. Non-Negative Matrix Factor Deconvolution; Extraction of Multiple Sound Sources from Monophonic Inputs. In 5th International Conference on Independent Component Analysis and Blind Signal Separation, Grenada, Spain, September 2004. Appears in Lecture Notes in Computer Science 3195 Springer 2004, ISBN3-540-23056-4, [PDF]
Brown, J.C.; Smaragdis, P., 2004. Independent Component Analysis for Automatic Note Extraction from Musical Trills, Journal of the Acoustical Society of America, Vol. 115, Issue 5, pp. 1851-2634,May 2004. [PDF]
Smaragdis, P. 2004. Exploiting Redundancy to Construct Listening Systems. In Perspectives on Speech Separation, Pierre Divenyi (ed.). Kluwer Academic Publishers (New York, USA). [Book link]

2003

Gaganis, V., N. Pasadakis, P. Smaragdis, N. Varotsis, 2003.Deconvolution of overlapping HPLC Peaks of Aromatic Hydrocarbons using Independent Component Analysis. Advances in Chromatography and Electrophoresis, Conferentia Chemometrica, Budapest, October 27-29, 2003. [PDF]
Smaragdis, P. and J.C. Brown, 2003. Non-negative Matrix Factorization for Polyphonic Music Transcription. In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, New Paltz, NY, October 19-22, 2003. [PDF]
Pasadakis, N., V. Gaganis, P. Smaragdis, 2003.Independent Component Analysis for Deconvolution of Overlapping HPLC Aromatic Peaks of Oil. 3rd International Conference of Instrumental Methods of Analysis (IMA 2003). Thessaloniki, Greece, September 23-27,2003. [PDF]
Brown, J.C. and P. Smaragdis, 2003, Independent Component Analysis for Automatic Extraction of Musical Information. Journal of the Acoustical Society of America, 2004 May, 115(5 Pt 1):2295-306. [PDF]
Smaragdis, P. and M. Casey, 2003. Audio/Visual Independent Components. 4th International Symposium on Independent Components Analysis and Blind Signal Separation, Nara, Japan April 1-5, 2003. [PDF]

2002

Whitman, B. and P. Smaragdis, 2002, Combining Musical and cultural Features for Intelligent Style Detection. 3rd International Conference on Music Information Retrieval 2002, Paris, France, October 13-17,2002. [PDF]

2001

Smaragdis, P. 2001, Redundancy Reduction for Computational Audition, a Unifying Approach, Ph.D. dissertation, MIT Media Lab. [PDF]

2000

Boulanger, R., P. Smaragdis and J. Fitch, 2000, Scanned Synthesis: an introduction and demonstration of a new synthesis and signal processing technique. In proceedings of the International Computer Music Conference 2000, Berlin, Germany, September, 2000. [PDF]
Smaragdis, P. 2000, Efficient Csound Programming, in The Csound Book eds. Richard Boulanger and Barry Vercoe, MIT Press. [Amazon link]

1999

Smaragdis, P. 1999, Information Theoretic Auditory Grouping,IJCAI-99 Workshop on Computational Auditory Scene Analysis. Stockholm, Sweden, August 1. [PDF]
Schobben, D.W.E., K. Torkkola and P. Smaragdis. 1999.Evaluation of Blind Signal Separation Methods First International Workshop on Independent Component Analysis and Blind Signal Separation, Aussois, France, January 11-15, 1999. [PDF]

1998

Smaragdis, P. 1998. Blind Separation of Convolved Mixtures in the Frequency Domain. International Workshop on Independence & Artificial Neural Networks University of La Laguna, Tenerife, Spain, February 9-10, 1998. Revised version appears in Neurocomputing Journal 22 (1998)21-34 . [PDF]

1997

Smaragdis, P. 1997. Efficient Blind Separation of Convolved Sound Mixtures, IEEE ASSP Workshop on Applications of Signal Processing to Audio and Acoustics. New Paltz NY, USA, October 1997. [PDF]
Smaragdis, P. 1997. Information Theoretic Approaches to Source Separation, Masters Thesis, MAS Department, Massachusetts Institute of Technology. [PDF]

1996

Casey, M. and P. Smaragdis, 1996. Netsound: Real-time audio from semantic descriptions, In proceedings of the International Computer Music Conference 1996, Kowloon, Hong-Kong, August 1996. [HTML]

Approved

#8,055,662 Method and System for Matching Audio Recording
#8,041,577 Method for Expanding Audio Signal Bandwidth
#8,015,003 Denoising Acoustic Signals Using Constrained Non-Negative Matrix Factorization
#7,937,270 System and Method for Recognizing Speech Securely
#7,698,143 Constructing Broadband Acoustic Signals from Lower-Band Acoustic Signals
#7,672,834 Method and System for Detecting and Temporally Relating Components in Non-Stationary Signals
#7,583,808 Locating and Tracking Acoustic Sources with Microphone Arrays
#7,526,084 Secure Classifying of Data with Gaussian Distributions
#7,475,014 Method and System for Tracing Signal Sources with Wrapped-Phase Hidden Markov Models
#7,415,392 System for Separating Multiple Sound Sources from Monophonic Input with Non-Negative Matrix Factor Deconvolution
#7,318,005 Shift-Invariant Probabilistic Component Analysis
#7,218,755 Detecting Temporally Related Components of Multimodal Signals
#6,934,651 Method for Synchronizing Signals Acquired from Unsynchronized Sensors

Pending

Noise-Robust Template Matching
Method of Clustering and Synchronizing Video Content of Multiple Events Using Audio
An online probabilistic latent component analysis algorithm for noise reduction in the presence of non-stationary noise
Semi-Supervised Source Separation Using Non-Negative Techniques
A Non-negative Approach to Semi-Supervised Separation of Speech from Noise with the Use of Temporal Dynamics
Non-negative Hidden Markov Modeling of Audio with Application to Source Separation
A Non-Negative and Time-Invariant Spectral Decomposition Approach to Acoustic Echo Cancellation
User-Guided Audio Selection from Complex Sound Mixtures
Joint Audio/Video Analysis and Editing
Relative Pitch Tracking of Multiple Arbitrary Sounds
Dynamic Range Extension Using Interleaved Gains
Surveillance System with Acoustically Augmented Video Monitoring
Cellular Telephone Based Surveillance System
Propagating Sound Information to Acoustically Isolated Environments
Identifying Component Groups with Independent Component Analysis of Chromatographic Data

Back to my home page
Paris Smaragdis