Follow
Penny Karanasou
Penny Karanasou
Speech Scientist, Amazon
Verified email at amazon.com - Homepage
Title
Cited by
Cited by
Year
Adaptation of deep neural network acoustic models using factorised i-vectors.
P Karanasou, Y Wang, MJF Gales, PC Woodland
Interspeech 2014, 2180-2184, 2014
782014
Stimulated Deep Neural Network for Speech Recognition
C Wu, P Karanasou, MJF Gales, KC Sim
Interspeech, 400-404, 2016
442016
Cambridge university transcription systems for the multi-genre broadcast challenge
PC Woodland, X Liu, Y Qian, C Zhang, MJF Gales, P Karanasou, ...
2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU …, 2015
372015
Improving interpretability and regularization in deep learning
C Wu, MJF Gales, A Ragni, P Karanasou, KC Sim
IEEE/ACM Transactions on Audio, Speech, and Language Processing 26 (2), 256-265, 2017
302017
An investigation into speaker informed DNN front-end for LVCSR
Y Liu, P Karanasou, T Hain
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
262015
Comparing SMT Methods for Automatic Generation of Pronunciation Variants
P Karanasou, L Lamel
International Conference on Natural Language Processing, 167-178, 2010
212010
Discriminatively trained phoneme confusion model for keyword spotting
P Karanasou, L Burget, D Vergyri, M Akbacak, A Mandal
INTERSPEECH, 2434-2437, 2012
202012
Cross-lingual Transfer Learning for Japanese Named Entity Recognition
A Johnson, P Karanasou, J Gaspers, D Klakow
Proceedings of NAACL-HLT 2019, 182–189, 2019
192019
Selecting Machine-Translated Data for Quick Bootstrapping of a Natural Language Understanding System
J Gaspers, P Karanasou, R Chatterjee
Proceedings of NAACL-HLT 2018, 137–144, 2018
182018
Improved DNN-based segmentation for multi-genre broadcast audio
L Wang, C Zhang, PC Woodland, MJF Gales, P Karanasou, P Lanchantin, ...
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016
172016
Selection of Multi-Genre Broadcast Data for the Training of Automatic Speech Recognition Systems
P Lanchantin, MJF Gales, P Karanasou, X Liu, Y Qian, L Wang, ...
Interspeech 2016, 3057-3061, 2016
172016
The development of the Cambridge University alignment systems for the Multi-Genre Broadcast challenge
P Lanchantin, MJF Gales, P Karanasou, X Liu, Y Qian, L Wang, ...
2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU …, 2015
172015
Speaker diarisation and longitudinal linking in multi-genre broadcast data
P Karanasou, MJF Gales, P Lanchantin, X Liu, Y Qian, L Wang, ...
2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU …, 2015
162015
Discriminative training of a phoneme confusion model for a dynamic lexicon in ASR
P Karanasou, F Yvon, T Lavergne, L Lamel
INTERSPEECH, 1966-1970, 2013
162013
I-vector estimation using informative priors for adaptation of deep neural networks
P Karanasou, M Gales, P Woodland
ISCA, 2015
112015
Prosodic representation learning and contextual sampling for neural text-to-speech
S Karlapati, A Abbas, Z Hodari, A Moinet, A Joly, P Karanasou, ...
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
102021
CAMP: A two-stage approach to modelling prosody in context
Z Hodari, A Moinet, S Karlapati, J Lorenzo-Trueba, T Merritt, A Joly, ...
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
102021
Combining i-vector representation and structured neural networks for rapid adaptation
C Wu, P Karanasou, MJF Gales
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016
102016
Phonemic variability and confusability in pronunciation modeling for automatic speech recognition
P Karanasou
Doctoral dissertation, Université Paris Sud-Paris XI, 2013
102013
Pronunciation variants generation using smt-inspired approaches
P Karanasou, L Lamel
ICASSP, 4908-4911, 2011
102011
The system can't perform the operation now. Try again later.
Articles 1–20