Evaluating Robustness to Noise and Compression of Deep Neural Networks for Keyword Spotting

Evaluating Robustness to Noise and Compression of Deep Neural Networks for Keyword Spotting

Keyword Spotting (KWS) has been the subject of research in recent years given the increase of embedded systems for command recognition such as Alexa, Google Home, and Siri. Performance, model size, processing time, and robustness to noise are fundamental in these systems. Furthermore, applications i...

Full description

Bibliographic Details
Main Authors: Pedro H. Pereira, Wesley Beccaro, Miguel A. Ramirez
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Speech recognition
machine learning algorithms
speech analysis
spectral analysis
pruning
quantization
Online Access:https://ieeexplore.ieee.org/document/10136724/

Internet

https://ieeexplore.ieee.org/document/10136724/

Similar Items