Md. Akmal Haidar
6 papers · 2014–2021 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
๐ Conference Polyglot (4) ๐ Interdisciplinary Bridge ๐งญ Keyword Pioneer ๐บ๏ธ Taxonomy Completionist (11) ๐ Academic Marathon (7)
๐
Cross-Pollinator
(8)
๐
Conference Pioneer
Conferences
INTERSPEECH (2)
NAACL (2)
COLING (1)
EMNLP (1)
Top co-authors
Keywords
language model
(2)
generative adversarial network
(2)
word error rate
(2)
text generation
(1)
automatic speech recognition
(1)
denoising autoencoder
(1)
recurrent neural network
(1)
latent space
(1)
word embedding
(1)
latent code
(1)
bidirectional translation
(1)
unsupervised machine translation
(1)
end-to-end speech recognition
(1)
self-knowledge distillation
(1)
transformer-based asr
(1)
time-reduction layer
(1)
language model fusion
(1)
model compression
(1)
soft text
(1)
matrix decomposition
(1)
Papers
Transformer-Based ASR Incorporating Time-Reduction Layer and Fine-Tuning with Self-Knowledge Distillation
INTERSPEECH 2021
Improving Word Embedding Factorization for Compression Using Distilled Nonlinear Neural Decomposition
EMNLP 2020
Bilingual-GAN: A Step Towards Parallel Text Generation
NAACL 2019
Latent Code and Text-based Generative Adversarial Networks for Soft-text Generation
NAACL 2019
Recurrent Neural Network Language Model with Incremental Updated Context Information Generated Using Bag-of-Words Representation
INTERSPEECH 2016
Interpolated Dirichlet Class Language Model for Speech Recognition Incorporating Long-distance N-grams
COLING 2014