Shashi Kumar
8 papers · 2019–2025 · 3 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 ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(21)
📈
Trend Setter
Venues
Top co-authors
Research topics
Speech & Audio
(7)
Deep Learning
(6)
Artificial Intelligence
(5)
Recognition
(5)
Machine Learning
(4)
Architectures
(4)
Core AI
(4)
Learning Paradigms
(3)
Learning Types · Deep Learning
(3)
Application Areas
(2)
Core Methods
(2)
Learning Types · Machine Learning
(2)
Synthesis
(2)
Natural Language Processing
(1)
Optimization & Theory
(1)
Keywords
automatic speech recognition
(6)
named entity recognition
(3)
word error rate
(3)
speech enhancement
(2)
domain adaptation
(2)
speech processing
(2)
variational autoencoder
(2)
semi-supervised learning
(2)
mean square error
(1)
multi-domain learning
(1)
latency-accuracy tradeoff
(1)
data filtering
(1)
end-to-end model
(1)
speaker adaptation
(1)
streaming asr
(1)
latency tradeoff
(1)
voice activity detection
(1)
speaker normalization
(1)
far-field speech
(1)
character error rate
(1)
Papers
Better Semi-supervised Learning for Multi-domain ASR Through Incremental Retraining and Data Filtering
Interspeech 2025
Efficient Data Selection for Domain Adaptation of ASR Using Pseudo-Labels and Multi-Stage Filtering
Interspeech 2025
Unifying Streaming and Non-streaming Zipformer-based ASR
ACL 2025
Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper
EMNLP 2024
TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer-based ASR
EMNLP 2024
Speaker Normalization Using Joint Variational Autoencoder
Interspeech 2021
Whisper Speech Enhancement Using Joint Variational Autoencoder for Improved Speech Recognition
Interspeech 2021
Far-Field Speech Enhancement Using Heteroscedastic Autoencoder for Improved Speech Recognition
Interspeech 2019