Data Augmentation for Deep Neural Network Acoustic Modeling

By Xiaodong Cui, Vaibhava Goel, Brian Kingsbury. 2015

77 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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. Zidong Wang
2. Xiaohui Liu
3. Yurong Liu
4. Fuad E. Alsaadi
5. Weibo Liu
6. Nianyin Zeng
7. Iqbal H. Sarker
8. Jinling Liang

In Speech & Audio

1. Fuad E. Alsaadi
2. Zidong Wang
3. Weibo Liu
4. Yurong Liu
5. Nianyin Zeng
6. Xiaohui Liu

In Signal Processing

1. Fuad E. Alsaadi
2. Zidong Wang
3. Weibo Liu
4. Yurong Liu
5. Nianyin Zeng
6. Xiaohui Liu

Citations in the corpus

• A survey of deep neural network architectures and their applications (2017, background): “(AVSR) systems [125], and data augmentation on the basis of l abel-preserving transformations [27].”
• Increasing generality in machine learning through procedural content generation (2019, unknown): “h cropping, padding, or adding noise to images in a dataset. It is common practice in machine learning and has resulted in signicantly less overtting and state-ofart results in a variety of domains [8, 35, 36]. A dierent form of data augmentation was introduced by Geirhos et al. [37], in which the a”