Lahiru Samarakoon
7 papers · 2016–2025 · 1 venue · 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 ↓+1 more ↓ Show less ↑
🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (17) 🧬 Topic Evolution 🏆 Keyword Champion (2)
🚀
Conference Pioneer
Venues
Top co-authors
Research topics
Speech & Audio
(7)
Deep Learning
(5)
Recognition
(4)
Machine Learning
(3)
Analysis · Speech & Audio
(3)
Architectures
(3)
Learning Types · Deep Learning
(2)
Learning Types · Machine Learning
(2)
Techniques
(2)
Artificial Intelligence
(1)
Computer Vision
(1)
Analysis · Computer Vision
(1)
Core AI
(1)
Core Methods
(1)
Keywords
speaker diarization
(4)
acoustic model
(3)
speaker adaptation
(3)
speaker embedding
(2)
end-to-end model
(2)
end-to-end diarization
(2)
encoder-decoder attractor
(2)
factorized hidden layer
(2)
deep neural network
(2)
diarization error rate
(1)
masked-attention transformer
(1)
conformer encoder
(1)
neural diarization
(1)
conversational summary
(1)
utterance-level information
(1)
attractor calculation
(1)
mask attention
(1)
parameter estimation
(1)
additive margin penalty
(1)
speech recognition
(1)
Papers
Pushing the Limits of End-to-End Diarization
Interspeech 2025
EEND-M2F: Masked-attention mask transformers for speaker diarization
Interspeech 2024
Improving End-to-End Neural Diarization Using Conversational Summary Representations
Interspeech 2023
Robust End-to-End Speaker Diarization with Conformer and Additive Margin Penalty
Interspeech 2021
Learning Factorized Transforms for Unsupervised Adaptation of LSTM-RNN Acoustic Models
Interspeech 2017
Multi-Attribute Factorized Hidden Layer Adaptation for DNN Acoustic Models
Interspeech 2016
Subspace LHUC for Fast Adaptation of Deep Neural Network Acoustic Models
Interspeech 2016