Pawel Swietojanski
Pawel Swietojanski
Research Scientist, Apple
Verified email at apple.com
Title
Cited by
Cited by
Year
LEARNING HIDDEN UNIT CONTRIBUTIONS FOR UNSUPERVISED SPEAKER ADAPTATION OF NEURAL NETWORK ACOUSTIC MODELS
P Swietojanski, S Renals
IEEE SLT, 2014
2242014
Multilingual training of Deep-Neural networks
A Ghoshal, P Swietojanski, S Renals
Proceedings of the IEEE International Conference on Acoustics, Speech and …, 2013
2132013
Convolutional neural networks for distant speech recognition
P Swietojanski, A Ghoshal, S Renals
Signal Processing Letters 21 (9), 1120-1124, 2014
2122014
Unsupervised cross-lingual knowledge transfer in DNN-based LVCSR
P Swietojanski, A Ghoshal, S Renals
2012 IEEE Spoken Language Technology Workshop (SLT), 246-251, 2012
1432012
A study of speaker adaptation for DNN-based speech synthesis
Z Wu, P Swietojanski, C Veaux, S Renals, S King
Proc. Interspeech, 2015
1372015
Hybrid acoustic models for distant and multichannel large vocabulary speech recognition
P Swietojanski, A Ghoshal, S Renals
In Proc. ASRU, 2013
1152013
Learning hidden unit contributions for unsupervised acoustic model adaptation
P Swietojanski, J Li, S Renals
IEEE/ACM Transactions on Audio, Speech, and Language Processing 24 (8), 1450 …, 2016
912016
Multi-task self-supervised learning for robust speech recognition
M Ravanelli, J Zhong, S Pascual, P Swietojanski, J Monteiro, J Trmal, ...
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
572020
NEURAL NETWORKS FOR DISTANT SPEECH RECOGNITION
S Renals, P Swietojanski
In Proc. HCSMA, 2014
482014
Investigation of Maxout Networks for Speech Recognition
P Swietojanski, J Li, JT Huang
Proceedings of the IEEE International Conference on Acoustics, Speech and …, 2014
482014
Multi-level adaptive networks in tandem and hybrid ASR systems
P Bell, P Swietojanski, S Renals
Proceedings of the IEEE International Conference on Acoustics, Speech and …, 2013
482013
Revisiting Hybrid and GMM-HMM system combination techniques
P Swietojanski, A Ghoshal, S Renals
Proceedings of the IEEE International Conference on Acoustics, Speech and …, 2013
462013
Benchmarking natural language understanding services for building conversational agents
X Liu, A Eshghi, P Swietojanski, V Rieser
arXiv preprint arXiv:1903.05566, 2019
452019
DIFFERENTIABLE POOLING FOR UNSUPERVISED SPEAKER ADAPTATION
P Swietojanski, S Renals
Proceedings of the IEEE International Conference on Acoustics, Speech and …, 2015
342015
Combining in-domain and out-of-domain speech data for automatic recognition of disordered speech
H Christensen, MB Aniol, P Bell, P Green, T Hain, S King, P Swietojanski
In Proc. Interspeech, 2013
342013
Unsupervised Adaptation of Recurrent Neural Network Language Models.
SR Gangireddy, P Swietojanski, P Bell, S Renals
Interspeech, 2333-2337, 2016
312016
Automatic Transcription of Multi-genre Media Archives
P Lanchantin, PJ Bell, MJF Gales, T Hain, X Liu, Y Long, J Quinnell, ...
312013
A lecture transcription system combining neural network acoustic and language models
P Bell, H Yamamoto, P Swietojanski, Y Wu, F McInnes, C Hori, S Renals
In Proc. Interspeech, 2013
302013
Transcription of multi-genre media archives using out-of-domain data
PJ Bell, MJF Gales, P Lanchantin, X Liu, Y Long, S Renals, ...
2012 IEEE Spoken Language Technology Workshop (SLT), 324-329, 2012
302012
Machine learning for predicting properties of porous media from 2d X-ray images
N Alqahtani, F Alzubaidi, RT Armstrong, P Swietojanski, P Mostaghimi
Journal of Petroleum Science and Engineering 184, 106514, 2020
292020
The system can't perform the operation now. Try again later.
Articles 1–20