Md. Akmal Haidar

According to our database1, Md. Akmal Haidar authored at least 31 papers between 2010 and 2022.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2022
RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation.
Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2022, 2022

Conformer with dual-mode chunked attention for joint online and offline ASR.
Proceedings of the Interspeech 2022, 2022

CILDA: Contrastive Data Augmentation Using Intermediate Layer Knowledge Distillation.
Proceedings of the 29th International Conference on Computational Linguistics, 2022

2021
Transformer-Based ASR Incorporating Time-Reduction Layer and Fine-Tuning with Self-Knowledge Distillation.
Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

Fine-Tuning of Pre-Trained End-to-End Speech Recognition with Generative Adversarial Networks.
Proceedings of the IEEE International Conference on Acoustics, 2021

Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

2020
From Unsupervised Machine Translation to Adversarial Text Generation.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Improving Word Embedding Factorization for Compression using Distilled Nonlinear Neural Decomposition.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2020, 2020

2019
Fully Quantizing a Simplified Transformer for End-to-end Speech Recognition.
CoRR, 2019

Distilled embedding: non-linear embedding factorization using knowledge distillation.
CoRR, 2019

TextKD-GAN: Text Generation using KnowledgeDistillation and Generative Adversarial Networks.
CoRR, 2019

Bilingual-GAN: A Step Towards Parallel Text Generation.
CoRR, 2019

Latent Code and Text-based Generative Adversarial Networks for Soft-text Generation.
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019

TextKD-GAN: Text Generation Using Knowledge Distillation and Generative Adversarial Networks.
Proceedings of the Advances in Artificial Intelligence, 2019

SALSA-TEXT: Self Attentive Latent Space Based Adversarial Text Generation.
Proceedings of the Advances in Artificial Intelligence, 2019

2018
Reg-Gan: Semi-Supervised Learning Based on Generative Adversarial Networks for Regression.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017
LDA-based context dependent recurrent neural network language model using document-based topic distribution of words.
Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

2016
Recurrent Neural Network Language Model with Incremental Updated Context Information Generated Using Bag-of-Words Representation.
Proceedings of the Interspeech 2016, 2016

2015
Unsupervised language model adaptation using LDA-based mixture models and latent semantic marginals.
Comput. Speech Lang., 2015

Document-specific context plsa language model for speech recognition.
Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

2014
Document-based Dirichlet class language model for speech recognition using document-based n-gram events.
Proceedings of the 2014 IEEE Spoken Language Technology Workshop, 2014

Novel topic n-gram count LM incorporating document-based topic distributions and n-gram counts.
Proceedings of the 22nd European Signal Processing Conference, 2014

Interpolated Dirichlet Class Language Model for Speech Recognition Incorporating Long-distance N-grams.
Proceedings of the COLING 2014, 2014

2013
Fitting long-range information using interpolated distanced n-grams and cache models into a latent dirichlet language model for speech recognition.
Proceedings of the INTERSPEECH 2013, 2013

Comparison of a bigram PLSA and a novel context-based PLSA language model for speech recognition.
Proceedings of the IEEE International Conference on Acoustics, 2013

PLSA enhanced with a long-distance bigram language model for speech recognition.
Proceedings of the 21st European Signal Processing Conference, 2013

2012
Topic n-gram count language model adaptation for speech recognition.
Proceedings of the 2012 IEEE Spoken Language Technology Workshop (SLT), 2012

LDA-based LM adaptation using latent semantic marginals and minimum discriminant information.
Proceedings of the 20th European Signal Processing Conference, 2012

2011
Unsupervised language model adaptation using latent Dirichlet allocation and dynamic marginals.
Proceedings of the 19th European Signal Processing Conference, 2011

Unsupervised language model adaptation using n-gram weighting.
Proceedings of the 24th Canadian Conference on Electrical and Computer Engineering, 2011

2010
Novel weighting scheme for unsupervised language model adaptation using latent dirichlet allocation.
Proceedings of the INTERSPEECH 2010, 2010


  Loading...