default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDMd. Akmal Haidar
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2022
[c26]Md. Akmal Haidar, Mehdi Rezagholizadeh, Abbas Ghaddar, Khalil Bibi, Philippe Langlais, Pascal Poupart:
CILDA: Contrastive Data Augmentation Using Intermediate Layer Knowledge Distillation. COLING 2022: 4707-4713- [c25]Felix Weninger, Marco Gaudesi, Md. Akmal Haidar, Nicola Ferri, Jesús Andrés-Ferrer, Puming Zhan:
Conformer with dual-mode chunked attention for joint online and offline ASR. INTERSPEECH 2022: 2053-2057 - [c24]Md. Akmal Haidar, Nithin Anchuri, Mehdi Rezagholizadeh, Abbas Ghaddar, Philippe Langlais, Pascal Poupart:
RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation. NAACL-HLT (Findings) 2022: 1389-1400 - [i11]Md. Akmal Haidar, Mehdi Rezagholizadeh, Abbas Ghaddar, Khalil Bibi, Philippe Langlais, Pascal Poupart:
CILDA: Contrastive Data Augmentation using Intermediate Layer Knowledge Distillation. CoRR abs/2204.07674 (2022) - 2021
- [c23]Yimeng Wu, Mehdi Rezagholizadeh, Abbas Ghaddar, Md. Akmal Haidar, Ali Ghodsi:
Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation. EMNLP (1) 2021: 7649-7661 - [c22]Md. Akmal Haidar, Mehdi Rezagholizadeh:
Fine-Tuning of Pre-Trained End-to-End Speech Recognition with Generative Adversarial Networks. ICASSP 2021: 6204-6208 - [c21]Md. Akmal Haidar, Chao Xing, Mehdi Rezagholizadeh:
Transformer-Based ASR Incorporating Time-Reduction Layer and Fine-Tuning with Self-Knowledge Distillation. Interspeech 2021: 2102-2106 - [i10]Md. Akmal Haidar, Chao Xing, Mehdi Rezagholizadeh:
Transformer-based ASR Incorporating Time-reduction Layer and Fine-tuning with Self-Knowledge Distillation. CoRR abs/2103.09903 (2021) - [i9]Md. Akmal Haidar, Mehdi Rezagholizadeh:
Fine-tuning of Pre-trained End-to-end Speech Recognition with Generative Adversarial Networks. CoRR abs/2103.13329 (2021) - [i8]Md. Akmal Haidar, Nithin Anchuri, Mehdi Rezagholizadeh, Abbas Ghaddar, Philippe Langlais, Pascal Poupart:
RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation. CoRR abs/2109.10164 (2021) - 2020
- [c20]Vasileios Lioutas, Ahmad Rashid, Krtin Kumar, Md. Akmal Haidar, Mehdi Rezagholizadeh:
Improving Word Embedding Factorization for Compression using Distilled Nonlinear Neural Decomposition. EMNLP (Findings) 2020: 2774-2784 - [c19]Ahmad Rashid, Alan Do-Omri, Md. Akmal Haidar, Qun Liu, Mehdi Rezagholizadeh:
From Unsupervised Machine Translation to Adversarial Text Generation. ICASSP 2020: 8194-8198 - [i7]Ahmad Rashid, Alan Do-Omri, Md. Akmal Haidar, Qun Liu, Mehdi Rezagholizadeh:
From Unsupervised Machine Translation To Adversarial Text Generation. CoRR abs/2011.05449 (2020)
2010 – 2019
- 2019
- [c18]Md. Akmal Haidar, Mehdi Rezagholizadeh:
TextKD-GAN: Text Generation Using Knowledge Distillation and Generative Adversarial Networks. Canadian AI 2019: 107-118 - [c17]Jules Gagnon-Marchand, Hamed Sadeghi, Md. Akmal Haidar, Mehdi Rezagholizadeh:
SALSA-TEXT: Self Attentive Latent Space Based Adversarial Text Generation. Canadian AI 2019: 119-131 - [c16]Md. Akmal Haidar, Mehdi Rezagholizadeh, Alan Do-Omri, Ahmad Rashid:
Latent Code and Text-based Generative Adversarial Networks for Soft-text Generation. NAACL-HLT (1) 2019: 2248-2258 - [i6]Ahmad Rashid, Alan Do-Omri, Md. Akmal Haidar, Qun Liu, Mehdi Rezagholizadeh:
Bilingual-GAN: A Step Towards Parallel Text Generation. CoRR abs/1904.04742 (2019) - [i5]Md. Akmal Haidar, Mehdi Rezagholizadeh, Alan Do-Omri, Ahmad Rashid:
Latent Code and Text-based Generative Adversarial Networks for Soft-text Generation. CoRR abs/1904.07293 (2019) - [i4]Md. Akmal Haidar, Mehdi Rezagholizadeh:
TextKD-GAN: Text Generation using KnowledgeDistillation and Generative Adversarial Networks. CoRR abs/1905.01976 (2019) - [i3]Vasileios Lioutas, Ahmad Rashid, Krtin Kumar, Md. Akmal Haidar, Mehdi Rezagholizadeh:
Distilled embedding: non-linear embedding factorization using knowledge distillation. CoRR abs/1910.06720 (2019) - [i2]Alex Bie, Bharat Venkitesh, Joao Monteiro, Md. Akmal Haidar, Mehdi Rezagholizadeh:
Fully Quantizing a Simplified Transformer for End-to-end Speech Recognition. CoRR abs/1911.03604 (2019) - 2018
- [c15]Mehdi Rezagholizadeh, Md. Akmal Haidar:
Reg-Gan: Semi-Supervised Learning Based on Generative Adversarial Networks for Regression. ICASSP 2018: 2806-2810 - [i1]Jules Gagnon-Marchand, Hamed Sadeghi, Md. Akmal Haidar, Mehdi Rezagholizadeh:
SALSA-TEXT : self attentive latent space based adversarial text generation. CoRR abs/1809.11155 (2018) - 2017
- [c14]Md. Akmal Haidar, Mikko Kurimo:
LDA-based context dependent recurrent neural network language model using document-based topic distribution of words. ICASSP 2017: 5730-5734 - 2016
- [c13]Md. Akmal Haidar, Mikko Kurimo:
Recurrent Neural Network Language Model with Incremental Updated Context Information Generated Using Bag-of-Words Representation. INTERSPEECH 2016: 3504-3508 - 2015
- [j1]Md. Akmal Haidar, Douglas D. O'Shaughnessy:
Unsupervised language model adaptation using LDA-based mixture models and latent semantic marginals. Comput. Speech Lang. 29(1): 20-31 (2015) - [c12]Md. Akmal Haidar, Douglas D. O'Shaughnessy:
Document-specific context plsa language model for speech recognition. ICASSP 2015: 5326-5330 - 2014
- [c11]Md. Akmal Haidar, Douglas D. O'Shaughnessy:
Interpolated Dirichlet Class Language Model for Speech Recognition Incorporating Long-distance N-grams. COLING 2014: 1793-1802 - [c10]Md. Akmal Haidar, Douglas D. O'Shaughnessy:
Novel topic n-gram count LM incorporating document-based topic distributions and n-gram counts. EUSIPCO 2014: 2310-2314 - [c9]Md. Akmal Haidar, Douglas D. O'Shaughnessy:
Document-based Dirichlet class language model for speech recognition using document-based n-gram events. SLT 2014: 42-47 - 2013
- [c8]Md. Akmal Haidar, Douglas D. O'Shaughnessy:
PLSA enhanced with a long-distance bigram language model for speech recognition. EUSIPCO 2013: 1-5 - [c7]Md. Akmal Haidar, Douglas D. O'Shaughnessy:
Comparison of a bigram PLSA and a novel context-based PLSA language model for speech recognition. ICASSP 2013: 8440-8444 - [c6]Md. Akmal Haidar, Douglas D. O'Shaughnessy:
Fitting long-range information using interpolated distanced n-grams and cache models into a latent dirichlet language model for speech recognition. INTERSPEECH 2013: 2678-2682 - 2012
- [c5]Md. Akmal Haidar, Douglas D. O'Shaughnessy:
LDA-based LM adaptation using latent semantic marginals and minimum discriminant information. EUSIPCO 2012: 2040-2044 - [c4]Md. Akmal Haidar, Douglas D. O'Shaughnessy:
Topic n-gram count language model adaptation for speech recognition. SLT 2012: 165-169 - 2011
- [c3]Md. Akmal Haidar, Douglas D. O'Shaughnessy:
Unsupervised language model adaptation using n-gram weighting. CCECE 2011: 857-860 - [c2]Md. Akmal Haidar, Douglas D. O'Shaughnessy:
Unsupervised language model adaptation using latent Dirichlet allocation and dynamic marginals. EUSIPCO 2011: 1480-1484 - 2010
- [c1]Md. Akmal Haidar, Douglas D. O'Shaughnessy:
Novel weighting scheme for unsupervised language model adaptation using latent dirichlet allocation. INTERSPEECH 2010: 2438-2441
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-04-24 23:12 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
