Mostafa Sadeghi

Publication Activity (10 Years)

Years Active: 2013-2025
Publications (10 Years): 56

Top Topics

Dictionary Learning

Generative Model

Speech Enhancement

Cellular Automata

Top Venues

IEEE Trans. Signal Process.

Publications

Simon Leglaive, Matthieu Fraticelli, Hend Elghazaly, Léonie Borne, Mostafa Sadeghi, Scott Wisdom, Manuel Pariente, John R. Hershey, Daniel Pressnitzer, Jon P. Barker
Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge. Comput. Speech Lang. 89 (2025)
Jean-Eudes Ayilo, Mostafa Sadeghi, Romain Serizel
Diffusion-Based Speech Enhancement with a Weighted Generative-Supervised Learning Loss. ICASSP (2024)
Mostafa Sadeghi, Xavier Alameda-Pineda, Radu Horaud
Unsupervised performance analysis of 3D face alignment with a statistically robust confidence test. Neurocomputing 564 (2024)
Mostafa Sadeghi, Romain Serizel
Posterior Sampling Algorithms for Unsupervised Speech Enhancement with Recurrent Variational Autoencoder. ICASSP (2024)
Can Cui, Imran A. Sheikh, Mostafa Sadeghi, Emmanuel Vincent
Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications. Odyssey (2024)
Can Cui, Imran A. Sheikh, Mostafa Sadeghi, Emmanuel Vincent
Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications. CoRR (2024)
Ali Golmakani, Mostafa Sadeghi, Xavier Alameda-Pineda, Romain Serizel
A Weighted-Variance Variational Autoencoder Model for Speech Enhancement. ICASSP (2024)
Berné Nortier, Mostafa Sadeghi, Romain Serizel
Unsupervised Speech Enhancement with Diffusion-Based Generative Models. ICASSP (2024)
Simon Leglaive, Matthieu Fraticelli, Hend Elghazaly, Léonie Borne, Mostafa Sadeghi, Scott Wisdom, Manuel Pariente, John R. Hershey, Daniel Pressnitzer, Jon P. Barker
Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge. CoRR (2024)
Mostafa Sadeghi, Romain Serizel
Fast and Efficient Speech Enhancement with Variational Autoencoders. ICASSP (2023)
Berné Nortier, Mostafa Sadeghi, Romain Serizel
Unsupervised speech enhancement with diffusion-based generative models. CoRR (2023)
Ali Golmakani, Mostafa Sadeghi, Romain Serizel
Audio-Visual Speech Enhancement with a Deep Kalman Filter Generative Model. ICASSP (2023)
Zhiqi Kang, Mostafa Sadeghi, Radu Horaud, Xavier Alameda-Pineda
Expression-Preserving Face Frontalization Improves Visually Assisted Speech Processing. Int. J. Comput. Vis. 131 (5) (2023)
Jean-Eudes Ayilo, Mostafa Sadeghi, Romain Serizel
Diffusion-based speech enhancement with a weighted generative-supervised learning loss. CoRR (2023)
Mostafa Sadeghi, Romain Serizel
Posterior sampling algorithms for unsupervised speech enhancement with recurrent variational autoencoder. CoRR (2023)
Can Cui, Sheikh Imran Ahamad, Mostafa Sadeghi, Emmanuel Vincent
End-to-end Multichannel Speaker-Attributed ASR: Speaker Guided Decoder and Input Feature Analysis. CoRR (2023)
Can Cui, Sheikh Imran Ahamad, Mostafa Sadeghi, Emmanuel Vincent
End-to-end Joint Rich and Normalized ASR with a limited amount of rich training data. CoRR (2023)
Simon Leglaive, Léonie Borne, Efthymios Tzinis, Mostafa Sadeghi, Matthieu Fraticelli, Scott Wisdom, Manuel Pariente, Daniel Pressnitzer, John R. Hershey
The CHiME-7 UDASE task: Unsupervised domain adaptation for conversational speech enhancement. CoRR (2023)
Can Cui, Imran A. Sheikh, Mostafa Sadeghi, Emmanuel Vincent
End-to-End Multichannel Speaker-Attributed ASR: Speaker Guided Decoder and Input Feature Analysis. ASRU (2023)
Zhiqi Kang, Mostafa Sadeghi, Radu Horaud, Xavier Alameda-Pineda, Jacob Donley, Anurag Kumar
The impact of removing head movements on audio-visual speech enhancement. CoRR (2022)
Mostafa Sadeghi, Paul Magron
A Sparsity-promoting Dictionary Model for Variational Autoencoders. INTERSPEECH (2022)
Mostafa Sadeghi, Romain Serizel
Fast and efficient speech enhancement with variational autoencoders. CoRR (2022)
Ali Golmakani, Mostafa Sadeghi, Romain Serizel
Audio-visual speech enhancement with a deep Kalman filter generative model. CoRR (2022)
Mostafa Sadeghi, Paul Magron
A Sparsity-promoting Dictionary Model for Variational Autoencoders. CoRR (2022)
Ali Golmakani, Mostafa Sadeghi, Xavier Alameda-Pineda, Romain Serizel
Weighted variance variational autoencoder for speech enhancement. CoRR (2022)
Zhiqi Kang, Mostafa Sadeghi, Radu Horaud, Xavier Alameda-Pineda, Jacob Donley, Anurag Kumar
The Impact of Removing Head Movements on Audio-Visual Speech Enhancement. ICASSP (2022)
Zhiqi Kang, Mostafa Sadeghi, Radu Horaud, Xavier Alameda-Pineda
Expression-preserving face frontalization improves visually assisted speech processing. CoRR (2022)
Sajjad Amini, Mohammad Soltanian, Mostafa Sadeghi, Shahrokh Ghaemmaghami
Non-Smooth Regularization: Improvement to Learning Framework Through Extrapolation. IEEE Trans. Signal Process. 70 (2022)
Mostafa Sadeghi, Xavier Alameda-Pineda
Switching Variational Auto-Encoders for Noise-Agnostic Audio-visual Speech Enhancement. CoRR (2021)
Mostafa Sadeghi, Xavier Alameda-Pineda
Mixture of Inference Networks for VAE-Based Audio-Visual Speech Enhancement. IEEE Trans. Signal Process. 69 (2021)
Mostafa Sadeghi, Xavier Alameda-Pineda
Switching Variational Auto-Encoders for Noise-Agnostic Audio-Visual Speech Enhancement. ICASSP (2021)
Zhiqi Kang, Radu Horaud, Mostafa Sadeghi
. ICCVW (2021)
Viet-Nhat Nguyen, Mostafa Sadeghi, Elisa Ricci, Xavier Alameda-Pineda
Deep Variational Generative Models for Audio-Visual Speech Separation. MLSP (2021)
Zhiqi Kang, Mostafa Sadeghi, Radu Horaud
Face Frontalization Based on Robustly Fitting a Deformable Shape Model to 3D Landmarks. CoRR (2020)
Mostafa Sadeghi, Simon Leglaive, Xavier Alameda-Pineda, Laurent Girin, Radu Horaud
Audio-Visual Speech Enhancement Using Conditional Variational Auto-Encoders. IEEE ACM Trans. Audio Speech Lang. Process. 28 (2020)
Mostafa Sadeghi, Xavier Alameda-Pineda
Robust Unsupervised Audio-Visual Speech Enhancement Using a Mixture of Variational Autoencoders. ICASSP (2020)
Javad Parsa, Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
Low Mutual and Average Coherence Dictionary Learning Using Convex Approximation. ICASSP (2020)
Mostafa Sadeghi, Massoud Babaie-Zadeh
Dictionary learning with low mutual coherence constraint. Neurocomputing 407 (2020)
Mostafa Sadeghi, Sylvain Guy, Adrien Raison, Xavier Alameda-Pineda, Radu Horaud
Unsupervised Performance Analysis of 3D Face Alignment. CoRR (2020)
Viet-Nhat Nguyen, Mostafa Sadeghi, Elisa Ricci, Xavier Alameda-Pineda
Deep Variational Generative Models for Audio-visual Speech Separation. CoRR (2020)
Mostafa Sadeghi, Keivan Navi, Mehdi Dolatshahi
Novel efficient full adder and full subtractor designs in quantum cellular automata. J. Supercomput. 76 (3) (2020)
Mostafa Sadeghi, Simon Leglaive, Xavier Alameda-Pineda, Laurent Girin, Radu Horaud
Audio-visual Speech Enhancement Using Conditional Variational Auto-Encoder. CoRR (2019)
Javad Parsa, Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
A New Algorithm for Dictionary Learning Based on Convex Approximation. EUSIPCO (2019)
Mostafa Sadeghi, Fateme Ghayem, Massoud Babaie-Zadeh, Saikat Chatterjee, Mikael Skoglund, Christian Jutten
LOSoft: ℓ0 Minimization via Soft Thresholding. EUSIPCO (2019)
Mostafa Sadeghi, Xavier Alameda-Pineda
Robust Unsupervised Audio-visual Speech Enhancement Using a Mixture of Variational Autoencoders. CoRR (2019)
Mostafa Sadeghi, Xavier Alameda-Pineda
Mixture of Inference Networks for VAE-based Audio-visual Speech Enhancement. CoRR (2019)
Saikat Chatterjee, Alireza M. Javid, Mostafa Sadeghi, Shumpei Kikuta, Partha P. Mitra, Mikael Skoglund
SSFN: Self Size-estimating Feed-forward Network and Low Complexity Design. CoRR (2019)
Fateme Ghayem, Mostafa Sadeghi, Massoud Babaie-Zadeh, Saikat Chatterjee, Mikael Skoglund, Christian Jutten
Sparse Signal Recovery Using Iterative Proximal Projection. IEEE Trans. Signal Process. 66 (4) (2018)
Javad Parsa, Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
Joint Low Mutual and Average Coherence Dictionary Learning. EUSIPCO (2018)
Elaheh Sobhani, Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
A robust ellipse fitting algorithm based on sparsity of outliers. EUSIPCO (2017)
Saikat Chatterjee, Alireza M. Javid, Mostafa Sadeghi, Partha P. Mitra, Mikael Skoglund
Progressive Learning for Systematic Design of Large Neural Networks. CoRR (2017)
Mostafa Sadeghi, Massoud Babaie-Zadeh
Incoherent Unit-Norm Frame Design via an Alternating Minimization Penalty Method. IEEE Signal Process. Lett. 24 (1) (2017)
Fateme Ghayem, Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
Accelerated Dictionary Learning for Sparse Signal Representation. LVA/ICA (2017)
Mohsen Joneidi, Parvin Ahmadi, Mostafa Sadeghi, Nazanin Rahnavard
Union of low-rank subspaces detector. IET Signal Process. 10 (1) (2016)
Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
Regularized low-coherence overcomplete dictionary learning for sparse signal decomposition. EUSIPCO (2016)
Mostafa Sadeghi, Massoud Babaie-Zadeh
Iterative Sparsification-Projection: Fast and Robust Sparse Signal Approximation. IEEE Trans. Signal Process. 64 (21) (2016)
Milad Niknejad, Mostafa Sadeghi, Massoud Babaie-Zadeh, Hossein Rabbani, Christian Jutten
A Dictionary Learning Method for Sparse Representation Using a Homotopy Approach. LVA/ICA (2015)
Hossein Bakhshi Golestani, Mohsen Joneidi, Mostafa Sadeghi
A Study on Clustering for Clustering Based Image De-Noising. CoRR (2015)
Mohsen Joneidi, Mostafa Sadeghi, Mojtaba Sahraee-Ardakan, Massoud Babaie-Zadeh, Christian Jutten
A study on clustering-based image denoising: From global clustering to local grouping. EUSIPCO (2014)
Jamal Golmohammady, Mohsen Joneidi, Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
K-LDA: An algorithm for learning jointly overcomplete and discriminative dictionaries. EUSIPCO (2014)
Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
Learning Overcomplete Dictionaries Based on Atom-by-Atom Updating. IEEE Trans. Signal Process. 62 (4) (2014)
Sajjad Amini, Mostafa Sadeghi, Mohsen Joneidi, Massoud Babaie-Zadeh, Christian Jutten
Outlier-aware dictionary learning for sparse representation. MLSP (2014)
Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
A new algorithm for learning overcomplete dictionaries. EUSIPCO (2013)
Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
Learning overcomplete dictionaries based on parallel atom-updating. MLSP (2013)
Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
Dictionary Learning for Sparse Representation: A Novel Approach. IEEE Signal Process. Lett. 20 (12) (2013)
Mohsen Joneidi, Parvin Ahmadi, Mostafa Sadeghi
A Union of Low-Rank Subspaces Detector: Application to Radar Signal Detection and Voice Activity Detection. CoRR (2013)
Mostafa Sadeghi, Mohsen Joneidi, Massoud Babaie-Zadeh, Christian Jutten
Sequential subspace finding: A new algorithm for learning low-dimensional linear subspaces. EUSIPCO (2013)