Preprints
[P1] C. Cui, I. A. Sheikh, M. Sadeghi, and E. Vincent, End-to-end Joint Rich and Normalized ASR with a Limited Amount of Rich Training Data, November, 2023. [Paper]
Journal papers
[J12] M. Sadeghi, X. Alameda-Pineda, and R. Horaud, Unsupervised Performance Analysis of 3D Face Alignment with a Statistically Robust Confidence Test, Neurocomputing, October 2023 (accepted for publication). [Paper, Code]
[J11] Z. Kang, M. Sadeghi, R. Horaud, and X. Alameda-Pineda, Expression-preserving Face Frontalization Improves Visually Assisted Speech Processing, International Journal of Computer Vision (IJCV), 2022. [Paper]
[J10] S. Amini, M. Soltanian, M. Sadeghi, S. Ghaemmaghami, Non-Smooth Regularization: Improvement to Learning Framework Through Extrapolation, IEEE Transactions on Signal Processing, vol. 70, pp. 1213–1223, February 2022.
[J9] M. Sadeghi and X. Alameda-Pineda, Mixture of Inference Networks for VAE-based Audio-visual Speech Enhancement, IEEE Transactions on Signal Processing, vol. 69, pp. 1899-1909, March 2021. [Code]
[J8] M. Sadeghi, S. Leglaive, X. Alameda-Pineda, L. Girin, and R. Horaud, Audio-visual Speech Enhancement Using Conditional Variational Auto-Encoders, IEEE Transactions on Audio, Speech and Language Processing, vol. 28, pp. 1788- 1800, May 2020. [Code]
[J7] M. Sadeghi and M. Babaie-Zadeh, Dictionary learning with low mutual coherence constraint, Neurocomputing, vol. 407, pp. 163-174, September 2020. [Code]
[J6] F. Ghayem, M. Sadeghi, M. Babaie-Zadeh, S. Chatterjee, M. Skoglund, and C. Jutten, Sparse Signal Recovery Using Iterative Proximal Projection, IEEE Transactions on Signal Processing, vol. 66. no. 4, pp. 879-894, February 2018. [Code]
[J5] M. Sadeghi and M. Babaie-Zadeh, Incoherent unit-norm frame design via an alternating minimization penalty method, IEEE Signal Processing Letters, vol. 24, no. 1, pp. 32-36, January 2017. [Code]
[J4] M. Sadeghi and M. Babaie-Zadeh, Iterative sparsification-projection: Fast and robust sparse signal approximation, IEEE Transactions on Signal Processing, vol. 64, no. 21, pp. 5536-5548, November 2016. [Code]
[J3] M. Joneidi, P. Ahmadi, M. Sadeghi, N. Rahnavard, Union of Low-rank Subspaces Detector, IET Signal Processing, vol. 10, no. 1, pp. 55-62, February 2016.
[J2] M. Sadeghi, M. Babaie-Zadeh, and C. Jutten, Learning Overcomplete Dictionaries Based on Atom-by-Atom Updating, IEEE Transactions on Signal Processing, vol. 62, no. 4, pp. 883-891, February 2014. [Code]
[J1] M. Sadeghi, M. Babaie-Zadeh, and C. Jutten, Dictionary Learning for Sparse Representation: A Novel Approach, IEEE Signal Processing Letters, vol. 20, no. 12, pp. 1195-1198, December 2013. (Nominated for IEEE SPL best paper award, 2017) [Code]
Conference papers
[C28] B. Nortier, M. Sadeghi, and R. Serizel, Unsupervised Speech Enhancement with Diffusion-based Generative Models, IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Seoul, Korea, April 2024. [Paper, Code, Supplementary Material]
[C27] J. E. Ayilo, M. Sadeghi, and R. Serizel, Diffusion-based Speech Enhancement with a Weighted Generative-Supervised Learning Loss, IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Seoul, Korea, April 2024. [Paper, Code]
[C26] M. Sadeghi and R. Serizel, Posterior Sampling Algorithms for Unsupervised Speech Enhancement with Recurrent Variational Autoencoder, IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Seoul, Korea, April 2024. [Paper, Code]
[C25] A. Golmakani, M. Sadeghi, X. Alameda-Pineda, and R. Serizel, A Weighted-variance Variational Autoencoder for Speech Enhancement, IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Seoul, Korea, April 2024. [Paper]
[C24] C. Cui, I. A. Sheikh, M. Sadeghi, and E. Vincent, End-to-end Multichannel Speaker-Attributed ASR: Speaker Guided Decoder and Input Feature Analysis, in IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Taipei, Taiwan, December 2023. [Paper]
[C23] S. Leglaive, L. Borne, E. Tzinis, M. Sadeghi, M. Fraticelli, S. Wisdom, M. Pariente, D. Pressnitzer, and J. R. Hershey, The CHiME-7 UDASE task: Unsupervised domain adaptation for conversational speech enhancement, 7th International Workshop on Speech Processing in Everyday Environments (CHiME), Dublin, Ireland, August 2023. [Paper, Website, Slides]
[C22] M. Sadeghi and R. Serizel, Fast and Efficient Speech Enhancement with Variational Autoencoders, IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Rhodes island, June 2023. [Paper, Code]
[C21] A. Golmakani, M. Sadeghi, and R. Serizel, Audio-visual Speech Enhancement with a Deep Kalman Filter Generative Model, IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Rhodes island, June 2023. [Paper, Code]
[C20] M. Sadeghi and P. Magron, A Sparsity-promoting Dictionary Model for Variational Autoencoders, Procedeeings of Interspeech, September 2022. [Paper, Poster, Code]
[C19] Z. Kang, M. Sadeghi, R. Horaud, J. Donley, A. Kumar, and X. Alameda-Pineda, The impact of removing head movements on audio-visual speech enhancement, IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), May 2022.
[C18] V.-N. Nguyen, M. Sadeghi, E. Ricci, and X. Alameda-Pineda, Deep variational generative models for audio-visual speech separation, IEEE International Workshop on Machine Learning for Signal Processing (MLSP), October 2021.
[C17] Z. Kang, R. Horaud, M. Sadeghi, Robust Face Frontalization For Visual Speech Recognition, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021.
[C16] M. Sadeghi and X. Alameda-Pineda, Switching Variational Auto-Encoders for Noise-Agnostic Audio-visual Speech Enhancement, IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Toronto, Ontario, Canada, June 2021. [Slides, Poster]
[C15] M. Sadeghi and X. Alameda-Pineda, Robust Unsupervised Audio-visual Speech Enhancement Using a Mixture of Variational Autoencoders, IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Barcelona, Spain, May 2020. [Slides]
[C14] J. Parsa, M. Sadeghi, M. Babaie-Zadeh, and C. Jutten, Low Mutual and Average Coherence Dictionary Learning Using Convex Approximation, IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Barcelona, Spain, May 2020.
[C13] J. Parsa, M. Sadeghi, M. Babaie-Zadeh, and C. Jutten, A New Algorithm for Dictionary Learning Based on Convex Approximation, Proceedings of the 27th European Signal Processing Conference (EUSIPCO), Coruña, Spain, 2-6 September 2019.
[C12] M. Sadeghi, F. Ghayem, M. Babaie-Zadeh, S. Chatterjee, M. Skoglund, and C. Jutten, L0Soft: L0 Minimization via Soft Thresholding, Proceedings of the 27th European Signal Processing Conference (EUSIPCO), 2-6 September 2019.
[C11] J. Parsa, M. Sadeghi, M. Babaie-Zadeh, and C. Jutten, Joint Low Mutual And Average Coherence Dictionary Learning, Proceedings of the 26th European Signal Processing Conference (EUSIPCO), Rome, Italy, 3-7 September 2018.
[C10] M. Sadeghi, C. R. Rojas, and B. Wahlberg, A Branch and Bound Approach to System Identification Based on Fixed-Rank Hankel Matrix Optimization, 18th IFAC Symposium on System Identification (SYSID), 2018.
[C9] F. Ghayem, M. Sadeghi, M. Babaie-Zadeh, and C. Jutten, Accelerated dictionary learning for sparse signal representation, 13th International Conference on Latent Variable Analysis and Signal Separation, LVA/ICA, Grenoble, France, 2017.
[C8] M. Sadeghi, M. Babaie-Zadeh, and C. Jutten, Regularized low-coherence overcomplete dictionary learning for sparse signal decomposition, Proceedings of 24th European Signal Processing Conference (EUSIPCO 2016), Budapest, Hungary, 2016.
[C7] M. Niknejad, M. Sadeghi, M. Babaie-Zadeh, H. Rabbani and C. Jutten, A dictionary learning method for sparse representation using a homotopy approach, 12th International Conference on Latent Variable Analysis and Signal Separation, LVA/ICA, Liberec, Czech Republic, 2016.
[C6] S. Amini, M. Sadeghi, M. Joneidi, M. Babaie-Zadeh, and C. Jutten, Outlier-aware dictionary learning for sparse representation, in IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2014), Reims, France, 2014.
[C5] M. Sadeghi, M. Babaie-Zadeh, and C. Jutten, Learning over-complete dictionaries based on parallel atom-updating, in Proceedings of 23rd IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2013), London, 2013.
[C4] M. Joneidi, M. Sadeghi, M. Sahraee, M. Babaie-Zadeh, and C. Jutten, A study on clustering-based image denoising: From global clustering to local grouping, in Proceedings 22nd European Signal Processing Conference (EUSIPCO 2014), Lisbon, Portugal, 2014.
[C3] M. Joneidi, J. Golmohammadi, M. Sadeghi, M. Babaie-Zadeh, and C. Jutten, K-LDA: An algorithm for Learning jointly reconstructive and discriminative dictionaries, in Proceedings 22nd European Signal Processing Conference (EUSIPCO 2014), Lisbon, Portugal, 2014.
[C2] M. Sadeghi, M. Joneidi, M. Babaie-Zadeh, and C. Jutten, Sequential subspace finding: A new algorithm for learning low-dimensional linear subspaces, in Proceedings of 21st European Signal Processing Conference (EUSIPCO 2013), Marrakesh, Morocco, 2013.
[C1] M. Sadeghi, M. Babaie-Zadeh, and C. Jutten, A new algorithm for learning over-complete dictionaries, in Proceedings of 21st European Signal Processing Conference (EUSIPCO 2013), Marrakesh, Morocco, 2013.
Unreviewed papers
[U1] S. Chatterjee, A. M. Javid, M. Sadeghi, S. Kikuta, P. P. Mitra, M. Skoglund, SSFN: Self Size-estimating Feed-forward Network and Low Complexity Design, March 2020. [Paper]