| 2022 | COLING | CILDA: Contrastive Data Augmentation Using Intermediate Layer Knowledge Distillation. | Md. Akmal Haidar, Mehdi Rezagholizadeh, Abbas Ghaddar, Khalil Bibi, Philippe Langlais, Pascal Poupart |
| 2022 | Interspeech | Conformer with dual-mode chunked attention for joint online and offline ASR. | Felix Weninger, Marco Gaudesi, Md. Akmal Haidar, Nicola Ferri, Jess Andrs-Ferrer, Puming Zhan |
| 2022 | NAACL | RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation. | Md. Akmal Haidar, Nithin Anchuri, Mehdi Rezagholizadeh, Abbas Ghaddar, Philippe Langlais, Pascal Poupart |
| 2021 | EMNLP | Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation. | Yimeng Wu, Mehdi Rezagholizadeh, Abbas Ghaddar, Md. Akmal Haidar, Ali Ghodsi |
| 2021 | ICASSP | Fine-Tuning of Pre-Trained End-to-End Speech Recognition with Generative Adversarial Networks. | Md. Akmal Haidar, Mehdi Rezagholizadeh |
| 2021 | Interspeech | Transformer-Based ASR Incorporating Time-Reduction Layer and Fine-Tuning with Self-Knowledge Distillation. | Md. Akmal Haidar, Chao Xing, Mehdi Rezagholizadeh |
| 2020 | EMNLP | Improving Word Embedding Factorization for Compression using Distilled Nonlinear Neural Decomposition. | Vasileios Lioutas, Ahmad Rashid, Krtin Kumar, Md. Akmal Haidar, Mehdi Rezagholizadeh |
| 2020 | ICASSP | From Unsupervised Machine Translation to Adversarial Text Generation. | Ahmad Rashid, Alan Do-Omri, Md. Akmal Haidar, Qun Liu, Mehdi Rezagholizadeh |
| 2019 | AI | SALSA-TEXT: Self Attentive Latent Space Based Adversarial Text Generation. | Jules Gagnon-Marchand, Hamed Sadeghi, Md. Akmal Haidar, Mehdi Rezagholizadeh |
| 2019 | AI | TextKD-GAN: Text Generation Using Knowledge Distillation and Generative Adversarial Networks. | Md. Akmal Haidar, Mehdi Rezagholizadeh |
| 2019 | NAACL | Latent Code and Text-based Generative Adversarial Networks for Soft-text Generation. | Md. Akmal Haidar, Mehdi Rezagholizadeh, Alan Do-Omri, Ahmad Rashid |
| 2018 | ICASSP | Reg-Gan: Semi-Supervised Learning Based on Generative Adversarial Networks for Regression. | Mehdi Rezagholizadeh, Md. Akmal Haidar |
| 2017 | ICASSP | LDA-based context dependent recurrent neural network language model using document-based topic distribution of words. | Md. Akmal Haidar, Mikko Kurimo |
| 2016 | Interspeech | Recurrent Neural Network Language Model with Incremental Updated Context Information Generated Using Bag-of-Words Representation. | Md. Akmal Haidar, Mikko Kurimo |
| 2015 | ICASSP | Document-specific context plsa language model for speech recognition. | Md. Akmal Haidar, Douglas D. O'Shaughnessy |
| 2014 | COLING | Interpolated Dirichlet Class Language Model for Speech Recognition Incorporating Long-distance N-grams. | Md. Akmal Haidar, Douglas D. O'Shaughnessy |
| 2013 | ICASSP | Comparison of a bigram PLSA and a novel context-based PLSA language model for speech recognition. | Md. Akmal Haidar, Douglas D. O'Shaughnessy |
| 2013 | Interspeech | Fitting long-range information using interpolated distanced n-grams and cache models into a latent dirichlet language model for speech recognition. | Md. Akmal Haidar, Douglas D. O'Shaughnessy |
| 2010 | Interspeech | Novel weighting scheme for unsupervised language model adaptation using latent dirichlet allocation. | Md. Akmal Haidar, Douglas D. O'Shaughnessy |