Somshubra Majumdar
10 papers · 2020–2026 · 4 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 ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (20)
🧬
Topic Evolution
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Machine Learning
(6)
Speech & Audio
(6)
Recognition
(6)
Deep Learning
(5)
Natural Language Processing
(4)
Architectures
(4)
Application Areas
(3)
Artificial Intelligence
(2)
Applications
(2)
Core AI
(2)
Learning Types · Machine Learning
(2)
Resources & Methods
(2)
Generation
(1)
Learning Types · Deep Learning
(1)
Models
(1)
Keywords
automatic speech recognition
(3)
large language model
(3)
speech translation
(3)
synthetic data generation
(2)
end-to-end model
(2)
multimodal learning
(1)
neural machine translation
(1)
data augmentation
(1)
efficient inference
(1)
batch normalization
(1)
instruction tuning
(1)
connectionist temporal classification
(1)
convolutional neural network
(1)
synthetic data
(1)
parameter efficiency
(1)
positional encoding
(1)
evolutionary algorithm
(1)
length extrapolation
(1)
residual network
(1)
code generation
(1)
Papers
Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models
ACL 2026
Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models
ACL 2025
SWAN: An Efficient and Scalable Approach for Long-Context Language Modeling
EMNLP 2025
Instruction Data Generation and Unsupervised Adaptation for Speech Language Models
Interspeech 2024
Less is More: Accurate Speech Recognition & Translation without Web-Scale Data
Interspeech 2024
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations
ICML 2023
CTC Variations Through New WFST Topologies
Interspeech 2022
NVIDIA NeMo Offline Speech Translation Systems for IWSLT 2022
ACL 2022
SPGISpeech: 5,000 Hours of Transcribed Financial Audio for Fully Formatted End-to-End Speech Recognition
Interspeech 2021
MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition
Interspeech 2020