Ankur Kumar
4 papers · 2020–2025 · 2 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Academic Marathon ยท Sprint
๐
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(10)
Venues
Top co-authors
Research topics
Keywords
binary classification
(1)
question answering
(1)
code generation
(1)
diffusion model
(1)
tabular data
(1)
agentic workflow
(1)
audio deepfake detection
(1)
confidence measure
(1)
word error rate
(1)
tabular question answering
(1)
end-to-end speech recognition
(1)
explainability technique
(1)
large language model
(1)
time-frequency representation
(1)
monotonic chunkwise attention
(1)
multi-agent system
(1)
sequence summary network
(1)
utterance invariant training
(1)
two-pass end-to-end speech recognition
(1)
bidirectional full-attention
(1)
Papers
A Data-Driven Diffusion-based Approach for Audio Deepfake Explanations
Interspeech 2025
Exploration Lab IITK at SemEval-2025 Task 8: Multi-LLM Agent QA over Tabular Data
SemEval 2025
Utterance Confidence Measure for End-to-End Speech Recognition with Applications to Distributed Speech Recognition Scenarios
Interspeech 2020
Utterance Invariant Training for Hybrid Two-Pass End-to-End Speech Recognition
Interspeech 2020