Fetching the paper…

Reading the bibliography…

2016

Active Learning for Speech Recognition: the Power of Gradients

Huang, Jiaji, Child, Rewon, Rao, Vinay et al.

Original
PDF
Post on X

Understand

In training speech recognition systems, labeling audio clips can be expensive, and not all data is equally valuable.

Active learning aims to label only the most informative samples to reduce cost.
For speech recognition, confidence scores and other likelihood-based active learning methods have been shown to be effective.
Gradient-based active learning methods, however, are still not well-understood.

Active Learning for Speech Recognition: the Power of Gradients · Around

Built on

The value of unlabeled data for classification problems
T. Zhang and F. Oles · 2000
Earlier work this paper cites.
Active learning: Theory and applications to automatic speech recognition
G. Riccardi and D. Hakkani-Tur · 2005
Earlier work this paper cites.
Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks
A. Graves, S. Fernandez, F. Gomez, and J. Schmidhuber · 2006
Earlier work this paper cites.

Similar

An analysis of active learning strategies for sequence labeling tasks
B. Settles and M. Craven · 2008
Cited alongside, same era.
Active learning literature survey
B. Settles · 2009
Cited alongside, same era.
Maximizing global entropy reduction for active learning in speech recognition
B. Varadarajan, D. Yu, L. Deng, and A. Acero · 2009
Cited alongside, same era.

Then

Stochastic optimization with importance sampling for regularized loss minimization
P. Zhao and T. Zhang · 2015
Later among the works it cites.
Deep speech 2 : End-to-end speech recognition in english and mandarin
D. Amodei, S. Ananthanarayanan, R. Anubhai, et al · 2016
Closest in time.
Asymptotic analysis of objectives based on fisher information in active learning
Original
J. Sourati, M. Akcakaya, T. K. Leen, D. Erdogmus, and J. G. Dy · 2016
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…