Md. Akmal Haidar

发表

Reg-Gan: Semi-Supervised Learning Based on Generative Adversarial Networks for Regression

Mehdi Rezagholiradeh, Md. Akmal Haidar, Mehdi Rezagholiradeh, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

LDA-based context dependent recurrent neural network language model using document-based topic distribution of words

Mikko Kurimo, Md. Akmal Haidar, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Fitting long-range information using interpolated distanced n-grams and cache models into a latent dirichlet language model for speech recognition

Douglas D. O'Shaughnessy, Md. Akmal Haidar, 2013, INTERSPEECH.

Comparison of a bigram PLSA and a novel context-based PLSA language model for speech recognition

Douglas D. O'Shaughnessy, Md. Akmal Haidar, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

PLSA enhanced with a long-distance bigram language model for speech recognition

Douglas D. O'Shaughnessy, Md. Akmal Haidar, 2013, 21st European Signal Processing Conference (EUSIPCO 2013).

Unsupervised language model adaptation using LDA-based mixture models and latent semantic marginals

Douglas D. O'Shaughnessy, Md. Akmal Haidar, 2015, Comput. Speech Lang..

Latent Code and Text-based Generative Adversarial Networks for Soft-text Generation

Mehdi Rezagholizadeh, Md. Akmal Haidar, Alan Do-Omri, 2019, NAACL.

SALSA-TEXT : self attentive latent space based adversarial text generation

Hamed Sadeghi, Mehdi Rezagholizadeh, Md. Akmal Haidar, 2018, Canadian AI.

Interpolated Dirichlet Class Language Model for Speech Recognition Incorporating Long-distance N-grams

Douglas D. O'Shaughnessy, Md. Akmal Haidar, D. O'Shaughnessy, 2014, COLING.

Bilingual-GAN: A Step Towards Parallel Text Generation pdf

Qun Liu, Mehdi Rezagholizadeh, Md. Akmal Haidar, 2019, Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation.

Novel topic n-gram count LM incorporating document-based topic distributions and n-gram counts

Douglas D. O'Shaughnessy, Md. Akmal Haidar, 2014, 2014 22nd European Signal Processing Conference (EUSIPCO).

Bilingual-GAN: Neural Text Generation and Neural Machine Translation as Two Sides of the Same Coin

Hamed Sadeghi, Mehdi Rezagholizadeh, Md. Akmal Haidar, 2018 .

Unsupervised language model adaptation using latent Dirichlet allocation and dynamic marginals

Douglas D. O'Shaughnessy, Md. Akmal Haidar, 2011, 2011 19th European Signal Processing Conference.

TextKD-GAN: Text Generation Using Knowledge Distillation and Generative Adversarial Networks pdf

Mehdi Rezagholizadeh, Md. Akmal Haidar, Mehdi Rezagholizadeh, 2019, Canadian Conference on AI.

Novel weighting scheme for unsupervised language model adaptation using latent dirichlet allocation

Douglas D. O'Shaughnessy, Md. Akmal Haidar, 2010, INTERSPEECH.

Document-specific context plsa language model for speech recognition

Douglas D. O'Shaughnessy, Md. Akmal Haidar, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Document-based Dirichlet class language model for speech recognition using document-based n-gram events

Douglas D. O'Shaughnessy, Md. Akmal Haidar, 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

Topic n-gram count language model adaptation for speech recognition

Douglas D. O'Shaughnessy, Md. Akmal Haidar, 2012, 2012 IEEE Spoken Language Technology Workshop (SLT).

Fully Quantizing a Simplified Transformer for End-to-end Speech Recognition pdf

Mehdi Rezagholizadeh, Md. Akmal Haidar, Joao Monteiro, 2019, ArXiv.

LDA-based LM adaptation using latent semantic marginals and minimum discriminant information

Douglas D. O'Shaughnessy, Md. Akmal Haidar, 2012, 2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO).

Recurrent Neural Network Language Model with Incremental Updated Context Information Generated Using Bag-of-Words Representation

Mikko Kurimo, Md. Akmal Haidar, M. Kurimo, 2016, INTERSPEECH.

Unsupervised language model adaptation using n-gram weighting

Douglas D. O'Shaughnessy, Md. Akmal Haidar, 2011, 2011 24th Canadian Conference on Electrical and Computer Engineering(CCECE).

From Unsupervised Machine Translation to Adversarial Text Generation

Qun Liu, Mehdi Rezagholizadeh, Md. Akmal Haidar, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation

Ali Ghodsi, Abbas Ghaddar, Md. Akmal Haidar, 2021, EMNLP.

Bilingual-GAN: A Step Towards Parallel Text Generation

Md. Akmal Haidar, Qun Liu, Ahmad Rashid, 2019, Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation.

A Simplified Fully Quantized Transformer for End-to-end Speech Recognition

Md. Akmal Haidar, Mehdi Rezagholizadeh, A. Bie, 2019, 1911.03604.

Transformer-based ASR Incorporating Time-reduction Layer and Fine-tuning with Self-Knowledge Distillation

Md. Akmal Haidar, Mehdi Rezagholizadeh, Chao Xing, 2021, Interspeech.

RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation pdf

Pascal Poupart, Philippe Langlais, Abbas Ghaddar, 2021, NAACL-HLT.

Conformer with dual-mode chunked attention for joint online and offline ASR

Md. Akmal Haidar, F. Weninger, P. Zhan, 2022, INTERSPEECH.