Robust Features in Deep-Learning-Based Speech Recognition

By V. Mitra, Horacio Franco, Richard M. Stern, Julien van Hout, Luciana Ferrer, M. Graciarena, Wen Wang, D. Vergyri, Abeer A. Alwan, John H. L. Hansen. 2017

36 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability, Speech & Audio, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Dan Hendrycks
2. Thomas G. Dietterich
3. Balaji Lakshminarayanan
4. Dawn Song
5. Nicholas Carlini
6. Yixuan Li
7. Matthias Hein
8. Igor Mordatch

In Safety, Robustness & Interpretability

1. Thomas G. Dietterich
2. Dan Hendrycks
3. Igor Mordatch
4. Yilun Du
5. Yixuan Li
6. Matthias Hein
7. Jacob Steinhardt
8. Mantas Mazeika

In Speech & Audio

1. Thomas G. Dietterich
2. Dan Hendrycks

In Signal Processing

1. Dan Hendrycks
2. Thomas G. Dietterich
3. Yilun Du
4. Igor Mordatch
5. Matthias Hein
6. Balaji Lakshminarayanan
7. Yixuan Li
8. Yedid Hoshen

Citations in the corpus

• Benchmarking Neural Network Robustness to Common Corruptions and Perturbations (2019, background): “Speech recognition research emphasizes robustness to common corruptions rather than worst-case, adversarial corruptions (Li et al., 2014; Mitra et al., 2017).”
• Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations (2018, background): “Speech recognition research emphasizes robustness to common corruptions over worst-case, adversarial corruptions [39, 46].”
• Brain tumor segmentation based on deep learning and an attention mechanism using MRI multi-modalities brain images (2021, background): “, pedestrian detection [15], [16], 80 speech recognition and understanding [17], [18], and brain tumor segmentation [19], [20].”