| Semi-supervised regression with generative adversarial networks M Rezagholizadeh, MA Haidar, D Wu US Patent 11,003,995, 2021 | 64* | 2021 |
| Textkd-gan: Text generation using knowledge distillation and generative adversarial networks MA Haidar, M Rezagholizadeh Advances in Artificial Intelligence: 32nd Canadian Conference on Artificial …, 2019 | 57 | 2019 |
| A simplified fully quantized transformer for end-to-end speech recognition A Bie, B Venkitesh, J Monteiro, MA Haidar, M Rezagholizadeh arXiv preprint arXiv:1911.03604, 2019 | 31* | 2019 |
| From unsupervised machine translation to adversarial text generation A Rashid, A Do-Omri, MA Haidar, Q Liu, M Rezagholizadeh ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 24* | 2020 |
| Latent code and text-based generative adversarial networks for soft-text generation MA Haidar, M Rezagholizadeh, A Do-Omri, A Rashid arXiv preprint arXiv:1904.07293, 2019 | 20 | 2019 |
| Salsa-text: self attentive latent space based adversarial text generation J Gagnon-Marchand, H Sadeghi, MA Haidar, M Rezagholizadeh Advances in Artificial Intelligence: 32nd Canadian Conference on Artificial …, 2019 | 18 | 2019 |
| Topic n-gram count language model adaptation for speech recognition MA Haidar, D O'Shaughnessy Spoken Language Technology Workshop (SLT), 2012 IEEE, 165-169, 2012 | 17 | 2012 |
| Unsupervised language model adaptation using LDA-based mixture models and latent semantic marginals MA Haidar, D O'Shaughnessy Computer Speech and Language, 2015 | 16 | 2015 |
| Universal-KD: Attention-based output-grounded intermediate layer knowledge distillation Y Wu, M Rezagholizadeh, A Ghaddar, MA Haidar, A Ghodsi Proceedings of the 2021 Conference on Empirical Methods in Natural Language …, 2021 | 15 | 2021 |
| Improving word embedding factorization for compression using distilled nonlinear neural decomposition V Lioutas, A Rashid, K Kumar, MA Haidar, M Rezagholizadeh arXiv preprint arXiv:1910.06720, 2019 | 15* | 2019 |
| Unsupervised language model adaptation using n-gram weighting MA Haidar, D O'Shaughnessy Electrical and Computer Engineering (CCECE), 2011 24th Canadian Conference …, 2011 | 14 | 2011 |
| RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation MA Haidar, N Anchuri, M Rezagholizadeh, A Ghaddar, P Langlais, ... Findings of the Association for Computational Linguistics: NAACL 2022, 2021 | 12 | 2021 |
| Bilingual-gan: A step towards parallel text generation A Rashid, A Do-Omri, MA Haidar, Q Liu, M Rezagholizadeh arXiv preprint arXiv:1904.04742, 2019 | 11 | 2019 |
| Novel Weighting Scheme for Unsupervised Language Model Adaptation Using Latent Dirichlet Allocation MA Haidar, D O'Shaughnessy Eleventh Annual Conference of the International Speech Communication …, 2010 | 11 | 2010 |
| Conformer with dual-mode chunked attention for joint online and offline asr F Weninger, M Gaudesi, MA Haidar, N Ferri, J Andrés-Ferrer, P Zhan arXiv preprint arXiv:2206.11157, 2022 | 8 | 2022 |
| Fine-tuning of pre-trained end-to-end speech recognition with generative adversarial networks MA Haidar, M Rezagholizadeh ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021 | 8 | 2021 |
| LDA-BASED LM ADAPTATION USING LATENT SEMANTIC MARGINALS AND MINIMUM DISCRIMINANT INFORMATION MA Haidar, D O’Shaughnessy EUSIPCO 2012, 2012 | 8 | 2012 |
| LDA-BASED CONTEXT DEPENDENT RECURRENT NEURAL NETWORK LANGUAGE MODEL USING DOCUMENT-BASED TOPIC DISTRIBUTION OF WORDS MA Haidar, M Kurimo ICASSP, 2017 | 7 | 2017 |
| COMPARISON OF A BIGRAM PLSA AND A NOVEL CONTEXT-BASED PLSA LANGUAGE MODEL FOR SPEECH RECOGNITION MA Haidar, D O’Shaughnessy ICASSP 2013, 2013 | 6 | 2013 |
| PLSA ENHANCED WITH A LONG-DISTANCE BIGRAM LANGUAGE MODEL FOR SPEECH RECOGNITION MA Haidar, D O'Shaughnessy EUSIPCO 2013, 2013 | 5 | 2013 |
Mehdi RezagholizadehPrincipal Research Scientist, Noah's Ark Lab, Huawei TechnologiesVerified email at mail.mcgill.ca
