Publications

35 / 3,734 publications found.


  •  Bralios, D., Tzinis, E., Wichern, G., Smaragdis, P., Le Roux, J., "Latent Iterative Refinement for Modular Source Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10096897, May 2023, pp. 1-5.
    BibTeX TR2023-019 PDF
    • @inproceedings{Bralios2023may,
    • author = {Bralios, Dimitrios and Tzinis, Efthymios and Wichern, Gordon and Smaragdis, Paris and Le Roux, Jonathan},
    • title = {Latent Iterative Refinement for Modular Source Separation},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10096897},
    • url = {https://www.merl.com/publications/TR2023-019}
    • }
  •  Tzinis, E., Wichern, G., Smaragdis, P., Le Roux, J., "Optimal Condition Training for Target Source Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10095128, May 2023, pp. 1-5.
    BibTeX TR2023-018 PDF
    • @inproceedings{Tzinis2023may,
    • author = {Tzinis, Efthymios and Wichern, Gordon and Smaragdis, Paris and Le Roux, Jonathan},
    • title = {Optimal Condition Training for Target Source Separation},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10095128},
    • url = {https://www.merl.com/publications/TR2023-018}
    • }
  •  Tzinis, E., Wichern, G., Subramanian, A.S., Smaragdis, P., Le Roux, J., "Heterogeneous Target Speech Separation", Interspeech, DOI: 10.21437/​Interspeech.2022-10717, September 2022, pp. 1796-1800.
    BibTeX TR2022-115 PDF Video Presentation
    • @inproceedings{Tzinis2022sep,
    • author = {Tzinis, Efthymios and Wichern, Gordon and Subramanian, Aswin Shanmugam and Smaragdis, Paris and Le Roux, Jonathan},
    • title = {Heterogeneous Target Speech Separation},
    • booktitle = {Interspeech},
    • year = 2022,
    • pages = {1796--1800},
    • month = sep,
    • doi = {10.21437/Interspeech.2022-10717},
    • url = {https://www.merl.com/publications/TR2022-115}
    • }
  •  Pathak, M.A., Raj, B., Rane, S., Samaragdis, P., "Privacy-preserving Speech Processing: Cryptographic and String-Matching Frameworks Show Promise", IEEE Signal Processing Magazine, March 2013.
    BibTeX TR2013-063 PDF
    • @article{Pathak2013feb,
    • author = {Pathak, M.A. and Raj, B. and Rane, S. and Samaragdis, P.},
    • title = {Privacy-preserving Speech Processing: Cryptographic and String-Matching Frameworks Show Promise},
    • journal = {IEEE Signal Processing Magazine},
    • year = 2013,
    • month = feb,
    • url = {https://www.merl.com/publications/TR2013-063}
    • }
  •  Wilson, K.W., Raj, B., Smaragdis, P., "Regularized Non-negative Matrix Factorization with Temporal Dependencies for Speech Denoising", Interspeech, September 2008.
    BibTeX TR2008-075 PDF
    • @inproceedings{Wilson2008sep,
    • author = {Wilson, K.W. and Raj, B. and Smaragdis, P.},
    • title = {Regularized Non-negative Matrix Factorization with Temporal Dependencies for Speech Denoising},
    • booktitle = {Interspeech},
    • year = 2008,
    • month = sep,
    • url = {https://www.merl.com/publications/TR2008-075}
    • }
  •  Wilson, K.W., Raj, B., Smaragdis, P., Divakaran, A., "Speech Denoising Using Nonnegative Matrix Factorization with Priors", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2008, pp. 4029-4032.
    BibTeX TR2008-012 PDF
    • @inproceedings{Wilson2008mar,
    • author = {Wilson, K.W. and Raj, B. and Smaragdis, P. and Divakaran, A.},
    • title = {Speech Denoising Using Nonnegative Matrix Factorization with Priors},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2008,
    • pages = {4029--4032},
    • month = mar,
    • issn = {1520-6149},
    • url = {https://www.merl.com/publications/TR2008-012}
    • }
  •  Smaragdis, P., Raj, B., Shashanka, M., "Sparse and Shift-Invariant Feature Extraction from Non-Negative Data", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2008, pp. 2069-2072.
    BibTeX TR2008-013 PDF
    • @inproceedings{Smaragdis2008mar,
    • author = {Smaragdis, P. and Raj, B. and Shashanka, M.},
    • title = {Sparse and Shift-Invariant Feature Extraction from Non-Negative Data},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2008,
    • pages = {2069--2072},
    • month = mar,
    • issn = {1520-6149},
    • url = {https://www.merl.com/publications/TR2008-013}
    • }
  •  Madhusudana Shashanka, Bhiksha Raj, Paris Smaragdis, "Probabilistic Latent Variable Models as Non-Negative Factorizations", Tech. Rep. TR2007-083, Mitsubishi Electric Research Laboratories, Cambridge, MA, December 2007.
    BibTeX TR2007-083 PDF
    • @techreport{MERL_TR2007-083,
    • author = {Madhusudana Shashanka, Bhiksha Raj, Paris Smaragdis},
    • title = {Probabilistic Latent Variable Models as Non-Negative Factorizations},
    • institution = {MERL - Mitsubishi Electric Research Laboratories},
    • address = {Cambridge, MA 02139},
    • number = {TR2007-083},
    • month = dec,
    • year = 2007,
    • url = {https://www.merl.com/publications/TR2007-083/}
    • }
  •  Paris Smaragdis, Bhiksha Raj, "Shift-Invariant Probabilistic Latent Component Analysis", Tech. Rep. TR2007-009, Mitsubishi Electric Research Laboratories, Cambridge, MA, December 2007.
    BibTeX TR2007-009 PDF
    • @techreport{MERL_TR2007-009,
    • author = {Paris Smaragdis, Bhiksha Raj},
    • title = {Shift-Invariant Probabilistic Latent Component Analysis},
    • institution = {MERL - Mitsubishi Electric Research Laboratories},
    • address = {Cambridge, MA 02139},
    • number = {TR2007-009},
    • month = dec,
    • year = 2007,
    • url = {https://www.merl.com/publications/TR2007-009/}
    • }
  •  Smaragdis, P., Raj, B., "Example-Driven Bandwidth Expansion", IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), October 2007, pp. 135-138.
    BibTeX TR2007-089 PDF
    • @inproceedings{Smaragdis2007oct,
    • author = {Smaragdis, P. and Raj, B.},
    • title = {Example-Driven Bandwidth Expansion},
    • booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},
    • year = 2007,
    • pages = {135--138},
    • month = oct,
    • isbn = {978-1-4244-1620-2},
    • url = {https://www.merl.com/publications/TR2007-089}
    • }
  •  Smaragdis, P., Shashanka, M., "A Framework for Secure Speech Recognition", IEEE Transactions on Audio, Speech and Language Processing, DOI: 10.1109/​TASL.2007.894526, Vol. 15, No. 4, pp. 1404-1413, May 2007.
    BibTeX TR2007-057 PDF
    • @article{Smaragdis2007may,
    • author = {Smaragdis, P. and Shashanka, M.},
    • title = {A Framework for Secure Speech Recognition},
    • journal = {IEEE Transactions on Audio, Speech and Language Processing},
    • year = 2007,
    • volume = 15,
    • number = 4,
    • pages = {1404--1413},
    • month = may,
    • doi = {10.1109/TASL.2007.894526},
    • issn = {1558-7916},
    • url = {https://www.merl.com/publications/TR2007-057}
    • }
  •  Raj, B., Singh, R., Shashanka, M., Smaragdis, P., "Bandwidth Expansion with a Polya URN Model", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2007, vol. 4, pp. IV597-IV600.
    BibTeX TR2007-058 PDF
    • @inproceedings{Raj2007apr,
    • author = {Raj, B. and Singh, R. and Shashanka, M. and Smaragdis, P.},
    • title = {Bandwidth Expansion with a Polya URN Model},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2007,
    • volume = 4,
    • pages = {IV597--IV600},
    • month = apr,
    • url = {https://www.merl.com/publications/TR2007-058}
    • }
  •  Shashanka, M.V.S., Raj, B., Smaragdis, P., "Sparse Overcomplete Decomposition for Single Channel Speaker Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2007, vol. 2, pp. 641-644.
    BibTeX TR2007-031 PDF
    • @inproceedings{Shashanka2007apr,
    • author = {Shashanka, M.V.S. and Raj, B. and Smaragdis, P.},
    • title = {Sparse Overcomplete Decomposition for Single Channel Speaker Separation},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2007,
    • volume = 2,
    • pages = {641--644},
    • month = apr,
    • issn = {1520-6149},
    • url = {https://www.merl.com/publications/TR2007-031}
    • }
  •  Smaragdis, P., Shashanka, M., "A Framework for Secure Speech Recognition", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2007, vol. 4, pp. 969-972.
    BibTeX IEEE Xplore
    • @inproceedings{Smaragdis2007apr,
    • author = {Smaragdis, P. and Shashanka, M.},
    • title = {A Framework for Secure Speech Recognition},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2007,
    • volume = 4,
    • pages = {969--972},
    • month = apr,
    • issn = {1520-6149},
    • url = {https://ieeexplore.ieee.org/document/4218264}
    • }
  •  Smaragdis, P., "Convolutive Speech Bases and their Application to Supervised Speech Separation", IEEE Transactions on Audio, Speech and Language Processing, Vol. 15, No. 1, pp. 1-12, January 2007.
    BibTeX TR2007-002 PDF
    • @article{Smaragdis2007jan2,
    • author = {Smaragdis, P.},
    • title = {Convolutive Speech Bases and their Application to Supervised Speech Separation},
    • journal = {IEEE Transactions on Audio, Speech and Language Processing},
    • year = 2007,
    • volume = 15,
    • number = 1,
    • pages = {1--12},
    • month = jan,
    • issn = {1558-7916},
    • url = {https://www.merl.com/publications/TR2007-002}
    • }
  •  Smaragdis, P., Boufounos, P., "Position and Trajectory Learning for Microphone Arrays", IEEE Transactions on Audio, Speech and Language Processing, Vol. 15, No. 1, pp. 358-368, January 2007.
    BibTeX TR2007-001 PDF
    • @article{Smaragdis2007jan1,
    • author = {Smaragdis, P. and Boufounos, P.},
    • title = {Position and Trajectory Learning for Microphone Arrays},
    • journal = {IEEE Transactions on Audio, Speech and Language Processing},
    • year = 2007,
    • volume = 15,
    • number = 1,
    • pages = {358--368},
    • month = jan,
    • issn = {1558-7916},
    • url = {https://www.merl.com/publications/TR2007-001}
    • }
  •  Smaragdis, P., Raj, B., Shashanka, M., "A Probabilistic Latent Variable Model for Acoustic Modeling", Advances in Neural Information Processing Systems (NIPS), December 2006.
    BibTeX TR2006-121 PDF
    • @inproceedings{Smaragdis2006dec,
    • author = {Smaragdis, P. and Raj, B. and Shashanka, M.},
    • title = {A Probabilistic Latent Variable Model for Acoustic Modeling},
    • booktitle = {Advances in Neural Information Processing Systems (NIPS)},
    • year = 2006,
    • month = dec,
    • url = {https://www.merl.com/publications/TR2006-121}
    • }
  •  Paris Smaragdis, Bhiksha Raj, Madhusudana Shashanka, "Supervised and Semi-Supervised Separation of Sounds from Single-Channel Mixtures", Tech. Rep. TR2007-062, Mitsubishi Electric Research Laboratories, Cambridge, MA, July 2006.
    BibTeX TR2007-062 PDF
    • @techreport{MERL_TR2007-062,
    • author = {Paris Smaragdis, Bhiksha Raj, Madhusudana Shashanka},
    • title = {Supervised and Semi-Supervised Separation of Sounds from Single-Channel Mixtures},
    • institution = {MERL - Mitsubishi Electric Research Laboratories},
    • address = {Cambridge, MA 02139},
    • number = {TR2007-062},
    • month = jul,
    • year = 2006,
    • url = {https://www.merl.com/publications/TR2007-062/}
    • }
  •  Raj, B., Shashanka, M.V.S., Smaragdis, P., "Latent Dirichlet Decomposition for Single Channel Speaker Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2006.
    BibTeX TR2006-064 PDF
    • @inproceedings{Raj2006may,
    • author = {Raj, B. and Shashanka, M.V.S. and Smaragdis, P.},
    • title = {Latent Dirichlet Decomposition for Single Channel Speaker Separation},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2006,
    • month = may,
    • url = {https://www.merl.com/publications/TR2006-064}
    • }
  •  Shashanka, M.V.S., Smaragdis, P., "Secure Sound Classification: Gaussian Mixture Models", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2006.
    BibTeX TR2006-065 PDF
    • @inproceedings{Shashanka2006may,
    • author = {Shashanka, M.V.S. and Smaragdis, P.},
    • title = {Secure Sound Classification: Gaussian Mixture Models},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2006,
    • month = may,
    • url = {https://www.merl.com/publications/TR2006-065}
    • }
  •  Radhakrishnan, R., Divakaran, A., Smaragdis, P., "Audio Analysis for Surveillance Applications", IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), October 2005, pp. 158-161.
    BibTeX TR2005-139 PDF
    • @inproceedings{Radhakrishnan2005oct,
    • author = {Radhakrishnan, R. and Divakaran, A. and Smaragdis, P.},
    • title = {Audio Analysis for Surveillance Applications},
    • booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},
    • year = 2005,
    • pages = {158--161},
    • month = oct,
    • url = {https://www.merl.com/publications/TR2005-139}
    • }
  •  Raj, B., Smaragdis, P., "Latent Variable Decomposition of Spectrograms for Single Channel Speaker Separation", IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), October 2005, pp. 17-20.
    BibTeX TR2005-137 PDF
    • @inproceedings{Raj2005oct,
    • author = {Raj, B. and Smaragdis, P.},
    • title = {Latent Variable Decomposition of Spectrograms for Single Channel Speaker Separation},
    • booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},
    • year = 2005,
    • pages = {17--20},
    • month = oct,
    • url = {https://www.merl.com/publications/TR2005-137}
    • }
  •  Smaragdis, P., Boufounos, P., "Learning Source Trajectories Using Wrapped-Phase Hidden Markov Models", IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), October 2005, pp. 114-117.
    BibTeX TR2005-138 PDF
    • @inproceedings{Smaragdis2005oct,
    • author = {Smaragdis, P. and Boufounos, P.},
    • title = {Learning Source Trajectories Using Wrapped-Phase Hidden Markov Models},
    • booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},
    • year = 2005,
    • pages = {114--117},
    • month = oct,
    • url = {https://www.merl.com/publications/TR2005-138}
    • }
  •  Bansal, D., Raj, B., Smaragdis, P., "Bandwidth Expansion of Narrowband Speech Using non-Negative Matrix Factorization", Eurospeech, September 2005.
    BibTeX TR2005-135 PDF
    • @inproceedings{Bansal2005sep,
    • author = {Bansal, D. and Raj, B. and Smaragdis, P.},
    • title = {Bandwidth Expansion of Narrowband Speech Using non-Negative Matrix Factorization},
    • booktitle = {Eurospeech},
    • year = 2005,
    • month = sep,
    • url = {https://www.merl.com/publications/TR2005-135}
    • }
  •  Raj, B., Singh, R., Smaragdis, P., "Recognizing Speech from Simultaneous Speakers", Eurospeech, September 2005.
    BibTeX TR2005-136 PDF
    • @inproceedings{Raj2005sep,
    • author = {Raj, B. and Singh, R. and Smaragdis, P.},
    • title = {Recognizing Speech from Simultaneous Speakers},
    • booktitle = {Eurospeech},
    • year = 2005,
    • month = sep,
    • url = {https://www.merl.com/publications/TR2005-136}
    • }