Mostafa Sadeghi

81 papers A 1C 2Misc 11Journal 45Unranked 22

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Diffusion-based Frameworks for Unsupervised Speech Enhancement. CoRR Jean-Eudes Ayilo, Mostafa Sadeghi, Romain Serizel, Xavier Alameda-Pineda
2025	—	`conf`	Creating Virtual Reality Environments at the Edge of the Metaverse. HICSS Mostafa Sadeghi
2025	C	`conf`	Data-independent Beamforming for End-to-end Multichannel Multi-speaker ASR. MMSP Can Cui, Paul Magron, Mostafa Sadeghi, Emmanuel Vincent
2025	J	`jnl`	Data-independent Beamforming for End-to-end Multichannel Multi-speaker ASR. CoRR Can Cui, Paul Magron, Mostafa Sadeghi, Emmanuel Vincent
2025	—	`conf`	Designing a Multiuser Security Education, Training, and Awareness (SETA) Module using Virtual Reality (VR). ECIS Mostafa Sadeghi, Hadi Ghanbari, Matti Rossi
2025	Misc	`conf`	Diffusion-based Unsupervised Audio-visual Speech Enhancement. ICASSP Jean-Eudes Ayilo, Mostafa Sadeghi, Romain Serizel, Xavier Alameda-Pineda
2025	—	`conf`	End-to-End Joint Punctuated and Normalized ASR with a Limited Amount of Punctuated Training Data. EUSIPCO Can Cui, Imran A. Sheikh, Mostafa Sadeghi, Emmanuel Vincent
2025	—	`conf`	Joint Beamforming and Speaker-Attributed ASR for Real Distant-Microphone Meeting Transcription. EUSIPCO Can Cui, Imran A. Sheikh, Mostafa Sadeghi, Emmanuel Vincent
2025	J	`jnl`	Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge. Comput. Speech Lang. Simon Leglaive, Matthieu Fraticelli, Hend Elghazaly, Léonie Borne, Mostafa Sadeghi, Scott Wisdom, Manuel Pariente, John R. Hershey, Daniel Pressnitzer, Jon P. Barker
2025	J	`jnl`	Posterior Transition Modeling for Unsupervised Diffusion-Based Speech Enhancement. CoRR Mostafa Sadeghi, Jean-Eudes Ayilo, Romain Serizel, Xavier Alameda-Pineda
2025	J	`jnl`	Posterior Transition Modeling for Unsupervised Diffusion-Based Speech Enhancement. IEEE Signal Process. Lett. Mostafa Sadeghi, Jean-Eudes Ayilo, Romain Serizel, Xavier Alameda-Pineda
2025	—	`conf`	Towards Skeletal and Signer Noise Reduction in Sign Language Production via Quaternion-Based Pose Encoding and Contrastive Learning. IVA (Adjunct) Guilhem Fauré, Mostafa Sadeghi, Sam Bigeard, Slim Ouni
2025	J	`jnl`	Towards Skeletal and Signer Noise Reduction in Sign Language Production via Quaternion-Based Pose Encoding and Contrastive Learning. CoRR Guilhem Fauré, Mostafa Sadeghi, Sam Bigeard, Slim Ouni
2024	Misc	`conf`	A Weighted-Variance Variational Autoencoder Model for Speech Enhancement. ICASSP Ali Golmakani, Mostafa Sadeghi, Xavier Alameda-Pineda, Romain Serizel
2024	Misc	`conf`	Diffusion-Based Speech Enhancement with a Weighted Generative-Supervised Learning Loss. ICASSP Jean-Eudes Ayilo, Mostafa Sadeghi, Romain Serizel
2024	J	`jnl`	Diffusion-based Unsupervised Audio-visual Speech Enhancement. CoRR Jean-Eudes Ayilo, Mostafa Sadeghi, Romain Serizel, Xavier Alameda-Pineda
2024	—	`conf`	Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications. Odyssey Can Cui, Imran A. Sheikh, Mostafa Sadeghi, Emmanuel Vincent
2024	J	`jnl`	Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications. CoRR Can Cui, Imran A. Sheikh, Mostafa Sadeghi, Emmanuel Vincent
2024	J	`jnl`	Joint Beamforming and Speaker-Attributed ASR for Real Distant-Microphone Meeting Transcription. CoRR Can Cui, Sheikh Imran Ahamad, Mostafa Sadeghi, Emmanuel Vincent
2024	J	`jnl`	Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge. CoRR Simon Leglaive, Matthieu Fraticelli, Hend Elghazaly, Léonie Borne, Mostafa Sadeghi, Scott Wisdom, Manuel Pariente, John R. Hershey, Daniel Pressnitzer, Jon P. Barker
2024	Misc	`conf`	Posterior Sampling Algorithms for Unsupervised Speech Enhancement with Recurrent Variational Autoencoder. ICASSP Mostafa Sadeghi, Romain Serizel
2024	—	`conf`	Security Education Training and Awareness (SETA) at the Edge of the Metaverse. ECIS Mostafa Sadeghi, Hadi Ghanbari, Matti Rossi
2024	Misc	`conf`	Unsupervised Speech Enhancement with Diffusion-Based Generative Models. ICASSP Berné Nortier, Mostafa Sadeghi, Romain Serizel
2024	J	`jnl`	Unsupervised performance analysis of 3D face alignment with a statistically robust confidence test. Neurocomputing Mostafa Sadeghi, Xavier Alameda-Pineda, Radu Horaud
2023	Misc	`conf`	Audio-Visual Speech Enhancement with a Deep Kalman Filter Generative Model. ICASSP Ali Golmakani, Mostafa Sadeghi, Romain Serizel
2023	J	`jnl`	Diffusion-based speech enhancement with a weighted generative-supervised learning loss. CoRR Jean-Eudes Ayilo, Mostafa Sadeghi, Romain Serizel
2023	C	`conf`	End-to-End Multichannel Speaker-Attributed ASR: Speaker Guided Decoder and Input Feature Analysis. ASRU Can Cui, Imran A. Sheikh, Mostafa Sadeghi, Emmanuel Vincent
2023	J	`jnl`	End-to-end Joint Rich and Normalized ASR with a limited amount of rich training data. CoRR Can Cui, Sheikh Imran Ahamad, Mostafa Sadeghi, Emmanuel Vincent
2023	J	`jnl`	End-to-end Multichannel Speaker-Attributed ASR: Speaker Guided Decoder and Input Feature Analysis. CoRR Can Cui, Sheikh Imran Ahamad, Mostafa Sadeghi, Emmanuel Vincent
2023	J	`jnl`	Expression-Preserving Face Frontalization Improves Visually Assisted Speech Processing. Int. J. Comput. Vis. Zhiqi Kang, Mostafa Sadeghi, Radu Horaud, Xavier Alameda-Pineda
2023	Misc	`conf`	Fast and Efficient Speech Enhancement with Variational Autoencoders. ICASSP Mostafa Sadeghi, Romain Serizel
2023	J	`jnl`	Posterior sampling algorithms for unsupervised speech enhancement with recurrent variational autoencoder. CoRR Mostafa Sadeghi, Romain Serizel
2023	J	`jnl`	The CHiME-7 UDASE task: Unsupervised domain adaptation for conversational speech enhancement. CoRR Simon Leglaive, Léonie Borne, Efthymios Tzinis, Mostafa Sadeghi, Matthieu Fraticelli, Scott Wisdom, Manuel Pariente, Daniel Pressnitzer, John R. Hershey
2023	J	`jnl`	Unsupervised speech enhancement with diffusion-based generative models. CoRR Berné Nortier, Mostafa Sadeghi, Romain Serizel
2022	A	`conf`	A Sparsity-promoting Dictionary Model for Variational Autoencoders. INTERSPEECH Mostafa Sadeghi, Paul Magron
2022	J	`jnl`	A Sparsity-promoting Dictionary Model for Variational Autoencoders. CoRR Mostafa Sadeghi, Paul Magron
2022	J	`jnl`	Audio-visual speech enhancement with a deep Kalman filter generative model. CoRR Ali Golmakani, Mostafa Sadeghi, Romain Serizel
2022	J	`jnl`	Expression-preserving face frontalization improves visually assisted speech processing. CoRR Zhiqi Kang, Mostafa Sadeghi, Radu Horaud, Xavier Alameda-Pineda
2022	J	`jnl`	Fast and efficient speech enhancement with variational autoencoders. CoRR Mostafa Sadeghi, Romain Serizel
2022	J	`jnl`	Non-Smooth Regularization: Improvement to Learning Framework Through Extrapolation. IEEE Trans. Signal Process. Sajjad Amini, Mohammad Soltanian, Mostafa Sadeghi, Shahrokh Ghaemmaghami
2022	Misc	`conf`	The Impact of Removing Head Movements on Audio-Visual Speech Enhancement. ICASSP Zhiqi Kang, Mostafa Sadeghi, Radu Horaud, Xavier Alameda-Pineda, Jacob Donley, Anurag Kumar
2022	J	`jnl`	The impact of removing head movements on audio-visual speech enhancement. CoRR Zhiqi Kang, Mostafa Sadeghi, Radu Horaud, Xavier Alameda-Pineda, Jacob Donley, Anurag Kumar
2022	J	`jnl`	Weighted variance variational autoencoder for speech enhancement. CoRR Ali Golmakani, Mostafa Sadeghi, Xavier Alameda-Pineda, Romain Serizel
2021	—	`conf`	Deep Variational Generative Models for Audio-Visual Speech Separation. MLSP Viet-Nhat Nguyen, Mostafa Sadeghi, Elisa Ricci, Xavier Alameda-Pineda
2021	J	`jnl`	Mixture of Inference Networks for VAE-Based Audio-Visual Speech Enhancement. IEEE Trans. Signal Process. Mostafa Sadeghi, Xavier Alameda-Pineda
2021	—	`conf`	Robust Face Frontalization For Visual Speech Recognition ICCVW Zhiqi Kang, Radu Horaud, Mostafa Sadeghi
2021	Misc	`conf`	Switching Variational Auto-Encoders for Noise-Agnostic Audio-Visual Speech Enhancement. ICASSP Mostafa Sadeghi, Xavier Alameda-Pineda
2021	J	`jnl`	Switching Variational Auto-Encoders for Noise-Agnostic Audio-visual Speech Enhancement. CoRR Mostafa Sadeghi, Xavier Alameda-Pineda
2020	J	`jnl`	Audio-Visual Speech Enhancement Using Conditional Variational Auto-Encoders. IEEE ACM Trans. Audio Speech Lang. Process. Mostafa Sadeghi, Simon Leglaive, Xavier Alameda-Pineda, Laurent Girin, Radu Horaud
2020	J	`jnl`	Deep Variational Generative Models for Audio-visual Speech Separation. CoRR Viet-Nhat Nguyen, Mostafa Sadeghi, Elisa Ricci, Xavier Alameda-Pineda
2020	J	`jnl`	Dictionary learning with low mutual coherence constraint. Neurocomputing Mostafa Sadeghi, Massoud Babaie-Zadeh
2020	J	`jnl`	Face Frontalization Based on Robustly Fitting a Deformable Shape Model to 3D Landmarks. CoRR Zhiqi Kang, Mostafa Sadeghi, Radu Horaud
2020	Misc	`conf`	Low Mutual and Average Coherence Dictionary Learning Using Convex Approximation. ICASSP Javad Parsa, Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
2020	J	`jnl`	Novel efficient full adder and full subtractor designs in quantum cellular automata. J. Supercomput. Mostafa Sadeghi, Keivan Navi, Mehdi Dolatshahi
2020	Misc	`conf`	Robust Unsupervised Audio-Visual Speech Enhancement Using a Mixture of Variational Autoencoders. ICASSP Mostafa Sadeghi, Xavier Alameda-Pineda
2019	—	`conf`	A New Algorithm for Dictionary Learning Based on Convex Approximation. EUSIPCO Javad Parsa, Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
2019	J	`jnl`	Audio-visual Speech Enhancement Using Conditional Variational Auto-Encoder. CoRR Mostafa Sadeghi, Simon Leglaive, Xavier Alameda-Pineda, Laurent Girin, Radu Horaud
2019	—	`conf`	LOSoft: ℓ0 Minimization via Soft Thresholding. EUSIPCO Mostafa Sadeghi, Fateme Ghayem, Massoud Babaie-Zadeh, Saikat Chatterjee, Mikael Skoglund, Christian Jutten
2019	J	`jnl`	Mixture of Inference Networks for VAE-based Audio-visual Speech Enhancement. CoRR Mostafa Sadeghi, Xavier Alameda-Pineda
2019	J	`jnl`	Robust Unsupervised Audio-visual Speech Enhancement Using a Mixture of Variational Autoencoders. CoRR Mostafa Sadeghi, Xavier Alameda-Pineda
2019	J	`jnl`	SSFN: Self Size-estimating Feed-forward Network and Low Complexity Design. CoRR Saikat Chatterjee, Alireza M. Javid, Mostafa Sadeghi, Shumpei Kikuta, Partha P. Mitra, Mikael Skoglund
2018	—	`conf`	Joint Low Mutual and Average Coherence Dictionary Learning. EUSIPCO Javad Parsa, Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
2018	J	`jnl`	Sparse Signal Recovery Using Iterative Proximal Projection. IEEE Trans. Signal Process. Fateme Ghayem, Mostafa Sadeghi, Massoud Babaie-Zadeh, Saikat Chatterjee, Mikael Skoglund, Christian Jutten
2017	—	`conf`	A robust ellipse fitting algorithm based on sparsity of outliers. EUSIPCO Elaheh Sobhani, Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
2017	—	`conf`	Accelerated Dictionary Learning for Sparse Signal Representation. LVA/ICA Fateme Ghayem, Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
2017	J	`jnl`	Incoherent Unit-Norm Frame Design via an Alternating Minimization Penalty Method. IEEE Signal Process. Lett. Mostafa Sadeghi, Massoud Babaie-Zadeh
2017	J	`jnl`	Progressive Learning for Systematic Design of Large Neural Networks. CoRR Saikat Chatterjee, Alireza M. Javid, Mostafa Sadeghi, Partha P. Mitra, Mikael Skoglund
2016	J	`jnl`	Iterative Sparsification-Projection: Fast and Robust Sparse Signal Approximation. IEEE Trans. Signal Process. Mostafa Sadeghi, Massoud Babaie-Zadeh
2016	—	`conf`	Regularized low-coherence overcomplete dictionary learning for sparse signal decomposition. EUSIPCO Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
2016	J	`jnl`	Union of low-rank subspaces detector. IET Signal Process. Mohsen Joneidi, Parvin Ahmadi, Mostafa Sadeghi, Nazanin Rahnavard
2015	—	`conf`	A Dictionary Learning Method for Sparse Representation Using a Homotopy Approach. LVA/ICA Milad Niknejad, Mostafa Sadeghi, Massoud Babaie-Zadeh, Hossein Rabbani, Christian Jutten
2015	J	`jnl`	A Study on Clustering for Clustering Based Image De-Noising. CoRR Hossein Bakhshi Golestani, Mohsen Joneidi, Mostafa Sadeghi
2014	—	`conf`	A study on clustering-based image denoising: From global clustering to local grouping. EUSIPCO Mohsen Joneidi, Mostafa Sadeghi, Mojtaba Sahraee-Ardakan, Massoud Babaie-Zadeh, Christian Jutten
2014	—	`conf`	K-LDA: An algorithm for learning jointly overcomplete and discriminative dictionaries. EUSIPCO Jamal Golmohammady, Mohsen Joneidi, Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
2014	J	`jnl`	Learning Overcomplete Dictionaries Based on Atom-by-Atom Updating. IEEE Trans. Signal Process. Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
2014	—	`conf`	Outlier-aware dictionary learning for sparse representation. MLSP Sajjad Amini, Mostafa Sadeghi, Mohsen Joneidi, Massoud Babaie-Zadeh, Christian Jutten
2013	J	`jnl`	A Union of Low-Rank Subspaces Detector: Application to Radar Signal Detection and Voice Activity Detection. CoRR Mohsen Joneidi, Parvin Ahmadi, Mostafa Sadeghi
2013	—	`conf`	A new algorithm for learning overcomplete dictionaries. EUSIPCO Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
2013	J	`jnl`	Dictionary Learning for Sparse Representation: A Novel Approach. IEEE Signal Process. Lett. Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
2013	—	`conf`	Learning overcomplete dictionaries based on parallel atom-updating. MLSP Mostafa Sadeghi, Massoud Babaie-Zadeh, Christian Jutten
2013	—	`conf`	Sequential subspace finding: A new algorithm for learning low-dimensional linear subspaces. EUSIPCO Mostafa Sadeghi, Mohsen Joneidi, Massoud Babaie-Zadeh, Christian Jutten