Word Order does not Matter for Speech Recognition. | 0 | 0.34 | 2022 |
Flashlight: Enabling Innovation in Tools for Machine Learning. | 0 | 0.34 | 2022 |
Pseudo-Labeling for Massively Multilingual Speech Recognition | 0 | 0.34 | 2022 |
CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings. | 0 | 0.34 | 2021 |
Robust wav2vec 2.0 - Analyzing Domain Shift in Self-Supervised Pre-Training. | 9 | 0.54 | 2021 |
Rethinking Evaluation in ASR - Are Our Models Robust Enough? | 2 | 0.38 | 2021 |
Kaizen: Continuously Improving Teacher Using Exponential Moving Average for Semi-Supervised Speech Recognition | 3 | 0.37 | 2021 |
slimIPL - Language-Model-Free Iterative Pseudo-Labeling. | 2 | 0.35 | 2021 |
SELF-TRAINING AND PRE-TRAINING ARE COMPLEMENTARY FOR SPEECH RECOGNITION | 0 | 0.34 | 2021 |
JOINT MASKED CPC AND CTC TRAINING FOR ASR | 0 | 0.34 | 2021 |
Iterative Pseudo-Labeling for Speech Recognition | 6 | 0.42 | 2020 |
Scaling Up Online Speech Recognition Using ConvNets | 1 | 0.35 | 2020 |
Who Needs Words? Lexicon-Free Speech Recognition. | 1 | 0.35 | 2019 |
Who Needs Words? Lexicon-Free Speech Recognition. | 0 | 0.34 | 2019 |
InfiniteBoost: building infinite ensembles with gradient descent. | 0 | 0.34 | 2017 |