Prati
Peter Bell
Peter Bell
University of Edinburgh
Potvrđena adresa e-pošte na ed.ac.uk - Početna stranica
Naslov
Citirano
Citirano
Godina
The MGB challenge: Evaluating multi-genre broadcast media recognition
P Bell, MJF Gales, T Hain, J Kilgour, P Lanchantin, X Liu, A McParland, ...
2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU …, 2015
1812015
Automatic dialect detection in arabic broadcast speech
A Ali, N Dehak, P Cardinal, S Khurana, SH Yella, J Glass, P Bell, ...
arXiv preprint arXiv:1509.06928, 2015
1432015
The MGB-2 challenge: Arabic multi-dialect broadcast media recognition
A Ali, P Bell, J Glass, Y Messaoui, H Mubarak, S Renals, Y Zhang
2016 IEEE Spoken Language Technology Workshop (SLT), 279-284, 2016
902016
Adaptation algorithms for neural network-based speech recognition: An overview
P Bell, J Fainberg, O Klejch, J Li, S Renals, P Swietojanski
IEEE Open Journal of Signal Processing 2, 33-66, 2020
642020
Sequence-to-sequence models for punctuated transcription combining lexical and acoustic features
O Klejch, P Bell, S Renals
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
642017
Improving Children's Speech Recognition Through Out-of-Domain Data Augmentation.
J Fainberg, P Bell, M Lincoln, S Renals
Interspeech, 1598-1602, 2016
642016
Combining in-domain and out-of-domain speech data for automatic recognition of disordered speech.
H Christensen, MB Aniol, P Bell, PD Green, T Hain, S King, ...
Interspeech, 3642-3645, 2013
632013
Regularization of context-dependent deep neural networks with context-independent multi-task training
P Bell, S Renals
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
602015
Multi-level adaptive networks in tandem and hybrid ASR systems
P Bell, P Swietojanski, S Renals
2013 IEEE international conference on acoustics, speech and signal …, 2013
542013
A grapheme-based method for automatic alignment of speech and text data
A Stan, P Bell, S King
2012 IEEE Spoken Language Technology Workshop (SLT), 286-290, 2012
482012
Punctuated transcription of multi-genre broadcasts using acoustic and lexical approaches
O Klejch, P Bell, S Renals
2016 IEEE Spoken Language Technology Workshop (SLT), 433-440, 2016
422016
On Learning Interpretable CNNs with Parametric Modulated Kernel-Based Filters.
E Loweimi, P Bell, S Renals
Interspeech, 3480-3484, 2019
412019
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
412012
ALISA: An automatic lightly supervised speech segmentation and alignment tool
A Stan, Y Mamiya, J Yamagishi, P Bell, O Watts, RAJ Clark, S King
Computer Speech & Language 35, 116-133, 2016
402016
Unsupervised Adaptation of Recurrent Neural Network Language Models.
SR Gangireddy, P Swietojanski, P Bell, S Renals
Interspeech, 2333-2337, 2016
362016
Multitask learning of context-dependent targets in deep neural network acoustic models
P Bell, P Swietojanski, S Renals
IEEE/ACM Transactions on Audio, Speech, and Language Processing 25 (2), 238-247, 2016
352016
Structured output layer with auxiliary targets for context-dependent acoustic modelling
P Swietojanski, P Bell, S Renals
Sixteenth Annual Conference of the International Speech Communication …, 2015
322015
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
Interspeech, 3087-3091, 2013
312013
Automatic transcription of multi-genre media archives
P Lanchantin, PJ Bell, MJF Gales, T Hain, X Liu, Y Long, J Quinnell, ...
312013
Learning to adapt: a meta-learning approach for speaker adaptation
O Klejch, J Fainberg, P Bell
arXiv preprint arXiv:1808.10239, 2018
302018
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20