Increasing the robustness of CNN acoustic models using autoregressive moving average spectrogram features and channel dropout

By György Kovács, László Tóth, Dirk Van Compernolle, Sriram Ganapathy. 2017

41 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Model Architectures, 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. Yu Zhang
2. Quoc V. Le
3. Chung-Cheng Chiu
4. Ekin Dogus Cubuk
5. William Chan
6. Barret Zoph
7. Yonghui Wu
8. Jinyu Li

In Model Architectures

1. Quoc V. Le
2. Ekin Dogus Cubuk
3. Barret Zoph
4. Yu Zhang
5. Chung-Cheng Chiu
6. William Chan
7. Frank Hutter
8. Song Han

In Speech & Audio

1. Yu Zhang
2. Chung-Cheng Chiu
3. Quoc V. Le
4. William Chan
5. Daniel S. Park
6. Yonghui Wu
7. Gabriel Synnaeve
8. Jinyu Li

In Signal Processing

1. Yu Zhang
2. Chung-Cheng Chiu
3. Quoc V. Le
4. William Chan
5. Yonghui Wu
6. Daniel S. Park
7. Tara N. Sainath
8. Jinyu Li

Citations in the corpus

• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition (2019, background): “ng them with longer schedules to address the under-fitting. Remark on related works. We note that an augmentation similar to frequency masking has been studied in the context of CNN acoustic models in [49]. There, blocks of adjacent frequencies are pre-grouped into bins, which are randomly zeroedout ”