Follow
Lahiru Samarakoon
Lahiru Samarakoon
Fano Labs, Hong Kong
Verified email at fano.ai
Title
Cited by
Cited by
Year
Factorized hidden layer adaptation for deep neural network based acoustic modeling
L Samarakoon, KC Sim
IEEE/ACM Transactions on Audio, Speech, and Language Processing 24 (12 …, 2016
732016
Subspace LHUC for Fast Adaptation of Deep Neural Network Acoustic Models.
L Samarakoon, KC Sim
Interspeech, 1593-1597, 2016
322016
On combining i-vectors and discriminative adaptation methods for unsupervised speaker normalization in DNN acoustic models
L Samarakoon, KC Sim
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016
272016
Learning factorized feature transforms for speaker normalization
L Samarakoon, KC Sim
2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU …, 2015
232015
Domain adaptation of end-to-end speech recognition in low-resource settings
L Samarakoon, B Mak, AYS Lam
2018 IEEE Spoken Language Technology Workshop (SLT), 382-388, 2018
222018
Adaptation of deep neural network acoustic models for robust automatic speech recognition
KC Sim, Y Qian, G Mantena, L Samarakoon, S Kundu, T Tan
New Era for Robust Speech Recognition: Exploiting Deep Learning, 219-243, 2017
172017
Automated question answering for customer helpdesk applications
L Samarakoon, S Kumarawadu, K Pulasinghe
2011 6th International Conference on Industrial and Information Systems, 328-333, 2011
152011
Robust End-to-End Speaker Diarization with Conformer and Additive Margin Penalty.
TY Leung, L Samarakoon
Interspeech, 3575-3579, 2021
102021
Learning Factorized Transforms for Unsupervised Adaptation of LSTM-RNN Acoustic Models.
L Samarakoon, B Mak, KC Sim
Interspeech, 744-748, 2017
82017
Improving end-to-end neural diarization using conversational summary representations
SJ Broughton, L Samarakoon
arXiv preprint arXiv:2306.13863, 2023
62023
Conformer-based speech recognition with linear nyström attention and rotary position embedding
L Samarakoon, TY Leung
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
62022
End-to-end speaker diarization system for the third dihard challenge system description
TY Leung, L Samarakoon
DIHARD III, 2021.[Online]. Available: https://dihardchallenge. github. io …, 2021
52021
Learning effective factorized hidden layer bases using student-teacher training for LSTM acoustic model adaptation
L Samarakoon, B Mak, KC Sim
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
52018
An investigation into learning effective speaker subspaces for robust unsupervised DNN adaptation
L Samarakoon, KC Sim, B Mak
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
52017
Multi-Attribute Factorized Hidden Layer Adaptation for DNN Acoustic Models.
L Samarakoon, KC Sim
Interspeech, 3484-3488, 2016
52016
Low-rank bases for factorized hidden layer adaptation of DNN acoustic models
L Samarakoon, KC Sim
2016 IEEE Spoken Language Technology Workshop (SLT), 652-658, 2016
42016
EEND-M2F: Masked-attention mask transformers for speaker diarization
M Härkönen, SJ Broughton, L Samarakoon
arXiv preprint arXiv:2401.12600, 2024
12024
Transformer Attractors for Robust and Efficient End-To-End Neural Diarization
L Samarakoon, SJ Broughton, M Härkönen, I Fung
2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 1-8, 2023
12023
Untied positional encodings for efficient transformer-based speech recognition
L Samarakoon, I Fung
2022 IEEE spoken language technology workshop (SLT), 108-114, 2023
12023
Incorporating Prior Knowledge into Speaker Diarization and Linking for Identifying Common Speaker
TY Leung, L Samarakoon, AYS Lam
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2019
12019
The system can't perform the operation now. Try again later.
Articles 1–20