Skip to main content

Approximate Neural Networks for Speech Applications in Resource-Constrained Environments


Abstract Speech recognition and keyword detection are becoming increasingly popular applications for mobile systems. While deep neural network (DNN) implementation of these systems have very good performance,

they have large memory and compute resource requirements, making their implementation on a mobile device quite challenging. In this thesis, techniques to reduce the memory and computation cost

of keyword detection and speech recognition networks (or DNNs) are presented.

The first technique is based on representing all weights and biases by a small number of bits and mapping all nodal computations into fixed-point ones with minimal degradation in the

accuracy. Experiments conducted on the Resource Management (RM) database show that for th... (more)
Created Date 2016
Contributor Arunachalam, Sairam (Author) / Chakrabarti, Chaitali (Advisor) / Seo, Jae-sun (Advisor) / Cao, Yu (Committee member) / Arizona State University (Publisher)
Subject Artificial intelligence / Deep Neural Networks / Keyword Detection / Memory Compression / Speech Recognition
Type Masters Thesis
Extent 52 pages
Language English
Copyright
Reuse Permissions All Rights Reserved
Note Masters Thesis Computer Science 2016
Collaborating Institutions Graduate College / ASU Library
Additional Formats MODS / OAI Dublin Core / RIS


  Full Text
738.8 KB application/pdf
Download Count: 765

Description Dissertation/Thesis