Theoretical learning guarantees applied to acoustic modeling

Theoretical learning guarantees applied to acoustic modeling

Abstract In low-resource scenarios, for example, small datasets or a lack in computational resources available, state-of-the-art deep learning methods for speech recognition have been known to fail. It is possible to achieve more robust models if care is taken to ensure the learning guarantees provi...

Full description

Bibliographic Details
Main Authors: Christopher D. Shulby, Martha D. Ferreira, Rodrigo F. de Mello, Sandra M. Aluisio
Format: Article
Language:English
Published: Sociedade Brasileira de Computação 2019-01-01
Series:Journal of the Brazilian Computer Society
Subjects:
Acoustic modeling
Convolutional neural networks
Shallow learning
Speech recognition
Statistical learning theory
Support vector machines
Online Access:http://link.springer.com/article/10.1186/s13173-018-0081-3

Internet

http://link.springer.com/article/10.1186/s13173-018-0081-3

Similar Items