Pratyush Kumar
22 papers · 2020–2024 · 7 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (47) π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Gold π¬ Deep Specialist (11)
π₯
Mega-Team Β· Squad
π€
Dynamic Duo
(16)
π
Renaissance Researcher
(6)
π₯
Unstoppable Β· Bronze
β‘
Prolific Year Β· Productive
π
Conference Pioneer
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(104)
Top co-authors
Research topics
Natural Language Processing
(13)
Artificial Intelligence
(12)
Resources & Methods
(12)
Machine Learning
(10)
Core AI
(10)
Deep Learning
(9)
Applications
(6)
Learning Types Β· Machine Learning
(6)
Techniques
(5)
Speech & Audio
(4)
Recognition
(4)
Application Areas
(3)
Architectures
(3)
Learning Paradigms
(3)
Learning Types Β· Deep Learning
(3)
Keywords
automatic speech recognition
(6)
indic language
(6)
indian language
(5)
multilingual nlp
(4)
low-resource language
(4)
natural language understanding
(3)
multilingual language model
(3)
multilingual model
(2)
transfer learning
(2)
multilingual speech
(2)
self-supervised learning
(2)
attention mechanism
(2)
benchmark evaluation
(2)
sign language recognition
(2)
pre-trained model
(2)
attention head
(2)
speech processing
(2)
multilingual pretraining
(2)
text generation
(2)
cross-lingual transfer
(2)
Papers
Empowering Low-Resource Language ASR via Large-Scale Pseudo Labeling
Interspeech 2024
IndicLLMSuite: A Blueprint for Creating Pre-training and Fine-Tuning Datasets for Indian Languages
ACL 2024
IndicVoices: Towards building an Inclusive Multilingual Speech Dataset for Indian Languages
ACL 2024
Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users
EMNLP 2023
IndicMT Eval: A Dataset to Meta-Evaluate Machine Translation Metrics for Indian Languages
ACL 2023
IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian Languages
AAAI 2023
Naamapadam: A Large-Scale Named Entity Annotated Data for Indic Languages
ACL 2023
Svarah: Evaluating English ASR Systems on Indian Accents
Interspeech 2023
Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages
ACL 2023
Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR
Interspeech 2023
Addressing Resource Scarcity across Sign Languages with Multilingual Pretraining and Unified-Vocabulary Datasets
NeurIPS 2022
IndicBART: A Pre-trained Model for Indic Natural Language Generation
ACL 2022
IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages
EMNLP 2022
Input-specific Attention Subnetworks for Adversarial Detection
ACL 2022
OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages
ACL 2022
Towards Building ASR Systems for the Next Billion Users
AAAI 2022
A Systematic Evaluation of Object Detection Networks for Scientific Plots
AAAI 2021
The Heads Hypothesis: A Unifying Statistical Approach Towards Understanding Multi-Headed Attention in BERT
AAAI 2021
IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages
EMNLP 2020
Joint Transformer/RNN Architecture for Gesture Typing in Indic Languages
COLING 2020
On the weak link between importance and prunability of attention heads
EMNLP 2020
PlotQA: Reasoning over Scientific Plots
WACV 2020