×
Dec 10, 2016 · This work investigates the Expected Gradient Length (EGL) approach in active learning for end-to-end speech recognition. We justify EGL from a ...
Sep 8, 2024 · Active learning aims to label only the most informative samples to reduce cost. For speech recognition, confidence scores and other likelihood- ...
This work investigates the Expected Gradient Length approach in active learning for end-to-end speech recognition, and justifies EGL from a variance ...
Dec 10, 2016 · This work investigates the Expected Gradient Length (EGL) approach in active learning for end-to-end speech recognition. We justify EGL from a ...
Jul 13, 2021 · Active learning for speech recognition: the power of gradients - Expected gradient length calculated with the model is a great measure ...
People also ask
In this paper, we propose an effective active learning query strategy for an automatic speech recognition system with the aim of reducing the training cost.
Missing: Power | Show results with:Power
Feb 13, 2024 · Context aware active learning of activity recognition models. In ... Active learning for speech recognition: the power of gradients.
In this paper, we propose an effective active learning query strategy for an automatic speech recognition system with the aim of reducing the training cost.
Missing: Power | Show results with:Power
Active learning aims at reducing the number of training examples to be labeled by automatically processing the unlabeled examples, and then selecting the most ...
Active Learning for Speech Recognition: the Power of Gradients‏. J Huang, R Child, V Rao, H Liu, S Satheesh, A Coates‏. arXiv preprint arXiv:1612.03226, 2016‏.