Prati
Daniel Povey
Daniel Povey
Chief Speech Scientist, Xiaomi Corp.
Potvrđena adresa e-pošte na xiaomi.com - Početna stranica
Naslov
Citirano
Citirano
Godina
The Kaldi speech recognition toolkit
D Povey, A Ghoshal, G Boulianne, L Burget, O Glembek, N Goel, ...
IEEE 2011 workshop on automatic speech recognition and understanding, 2011
74582011
Librispeech: an asr corpus based on public domain audio books
V Panayotov, G Chen, D Povey, S Khudanpur
2015 IEEE international conference on acoustics, speech and signal …, 2015
66512015
The HTK book
S Young, G Evermann, M Gales, T Hain, D Kershaw, X Liu, G Moore, ...
Cambridge university engineering department 3 (175), 12, 2002
40832002
The HTK book
S Young, G Evermann, M Gales, T Hain, D Kershaw, X Liu, G Moore, ...
Available on, 1999
34001999
X-vectors: Robust dnn embeddings for speaker recognition
D Snyder, D Garcia-Romero, G Sell, D Povey, S Khudanpur
2018 IEEE international conference on acoustics, speech and signal …, 2018
31752018
Musan: A music, speech, and noise corpus
D Snyder, G Chen, D Povey
arXiv preprint arXiv:1510.08484, 2015
14422015
Audio augmentation for speech recognition.
T Ko, V Peddinti, D Povey, S Khudanpur
Interspeech 2015, 3586, 2015
13742015
A time delay neural network architecture for efficient modeling of long temporal contexts.
V Peddinti, D Povey, S Khudanpur
Interspeech, 3214-3218, 2015
13412015
A study on data augmentation of reverberant speech for robust speech recognition
T Ko, V Peddinti, D Povey, ML Seltzer, S Khudanpur
2017 IEEE international conference on acoustics, speech and signal …, 2017
10782017
Deep neural network embeddings for text-independent speaker verification.
D Snyder, D Garcia-Romero, D Povey, S Khudanpur
Interspeech 2017, 999-1003, 2017
10622017
Purely sequence-trained neural networks for ASR based on lattice-free MMI.
D Povey, V Peddinti, D Galvez, P Ghahremani, V Manohar, X Na, Y Wang, ...
Interspeech, 2751-2755, 2016
9982016
Sequence-discriminative training of deep neural networks.
K Veselý, A Ghoshal, L Burget, D Povey
Interspeech 2013, 2345-2349, 2013
9372013
Minimum phone error and I-smoothing for improved discriminative training
D Povey, PC Woodland
2002 IEEE international conference on acoustics, speech, and signal …, 2002
9132002
Strategies for training large scale neural network language models
T Mikolov, A Deoras, D Povey, L Burget, J Černocký
2011 IEEE Workshop on Automatic Speech Recognition & Understanding, 196-201, 2011
7192011
Discriminative training for large vocabulary speech recognition
D Povey
University of Cambridge, 2005
7082005
Semi-orthogonal low-rank matrix factorization for deep neural networks.
D Povey, G Cheng, Y Wang, K Li, H Xu, M Yarmohammadi, S Khudanpur
Interspeech, 3743-3747, 2018
6202018
Large scale discriminative training of hidden Markov models for speech recognition
PC Woodland, D Povey
Computer Speech & Language 16 (1), 25-47, 2002
5662002
Boosted MMI for model and feature-space discriminative training
D Povey, D Kanevsky, B Kingsbury, B Ramabhadran, G Saon, ...
2008 IEEE International Conference on Acoustics, Speech and Signal …, 2008
4972008
Deep neural network-based speaker embeddings for end-to-end speaker verification
D Snyder, P Ghahremani, D Povey, D Garcia-Romero, Y Carmiel, ...
2016 IEEE spoken language technology workshop (SLT), 165-170, 2016
4442016
Parallel training of DNNs with natural gradient and parameter averaging
D Povey, X Zhang, S Khudanpur
arXiv preprint arXiv:1410.7455, 2014
4052014
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20