Lahiru Samarakoon

According to our database, Lahiru Samarakoon authored at least 23 papers between 2015 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Configurable Multilingual ASR with Speech Summary Representations.

Harrison Zhu, Ivan Fung, Yingke Zhu, Lahiru Samarakoon

CoRR, 2024

EEND-M2F: Masked-attention mask transformers for speaker diarization.

Marc Härkönen, Samuel J. Broughton, Lahiru Samarakoon

CoRR, 2024

2023

Improving End-to-End Neural Diarization Using Conversational Summary Representations.

Samuel J. Broughton, Lahiru Samarakoon

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

Improving Non-Autoregressive Speech Recognition with Autoregressive Pretraining.

Yanjia Li, Lahiru Samarakoon, Ivan Fung

Proceedings of the IEEE International Conference on Acoustics, 2023

Transformer Attractors for Robust and Efficient End-To-End Neural Diarization.

Lahiru Samarakoon, Samuel J. Broughton, Marc Härkönen, Ivan Fung

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

Robust End-to-End Diarization with Domain Adaptive Training and Multi-Task Learning.

Ivan Fung, Lahiru Samarakoon, Samuel J. Broughton

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

2022

Untied Positional Encodings for Efficient Transformer-Based Speech Recognition.

Lahiru Samarakoon, Ivan Fung

Proceedings of the IEEE Spoken Language Technology Workshop, 2022

Conformer-Based Speech Recognition with Linear Nyström Attention and Rotary Position Embedding.

Lahiru Samarakoon, Tsun-Yat Leung

Proceedings of the IEEE International Conference on Acoustics, 2022

2021

Robust End-to-End Speaker Diarization with Conformer and Additive Margin Penalty.

Tsun-Yat Leung, Lahiru Samarakoon

Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

2019

Incorporating Prior Knowledge into Speaker Diarization and Linking for Identifying Common Speaker.

Tsun-Yat Leung, Lahiru Samarakoon, Albert Y. S. Lam

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2019

2018

Domain Adaptation of End-to-end Speech Recognition in Low-Resource Settings.

Lahiru Samarakoon, Brian Mak, Albert Y. S. Lam

Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

Subspace Based Sequence Discriminative Training of LSTM Acoustic Models with Feed-Forward Layers.

Lahiru Samarakoon, Brian Mak, Albert Y. S. Lam

Proceedings of the 11th International Symposium on Chinese Spoken Language Processing, 2018

learning Effective Factorized Hidden Layer Bases Using Student-Teacher Training for LSTM Acoustic Model Adaptation.

Lahiru Samarakoon, Brian Mak, Khe Chai Sim

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017

Learning Factorized Transforms for Unsupervised Adaptation of LSTM-RNN Acoustic Models.

Lahiru Samarakoon, Brian Mak, Khe Chai Sim

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

An investigation into learning effective speaker subspaces for robust unsupervised DNN adaptation.

Lahiru Samarakoon, Khe Chai Sim, Brian Mak

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Unsupervised adaptation of student DNNS learned from teacher RNNS for improved ASR performance.

Lahiru Samarakoon, Brian Mak

Proceedings of the 2017 IEEE Automatic Speech Recognition and Understanding Workshop, 2017

Adaptation of Deep Neural Network Acoustic Models for Robust Automatic Speech Recognition.

Khe Chai Sim, Yanmin Qian, Gautam Mantena, Lahiru Samarakoon, Souvik Kundu, Tian Tan

Proceedings of the New Era for Robust Speech Recognition, Exploiting Deep Learning., 2017

2016

Factorized Hidden Layer Adaptation for Deep Neural Network Based Acoustic Modeling.

Lahiru Samarakoon, Khe Chai Sim

IEEE ACM Trans. Audio Speech Lang. Process., 2016

Low-rank bases for factorized hidden layer adaptation of DNN acoustic models.

Lahiru Samarakoon, Khe Chai Sim

Proceedings of the 2016 IEEE Spoken Language Technology Workshop, 2016

Multi-Attribute Factorized Hidden Layer Adaptation for DNN Acoustic Models.

Lahiru Samarakoon, Khe Chai Sim

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

Subspace LHUC for Fast Adaptation of Deep Neural Network Acoustic Models.

Lahiru Samarakoon, Khe Chai Sim

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

On combining i-vectors and discriminative adaptation methods for unsupervised speaker normalization in DNN acoustic models.

Lahiru Samarakoon, Khe Chai Sim

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2015

Learning factorized feature transforms for speaker normalization.

Lahiru Samarakoon, Khe Chai Sim

Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, 2015