ISIS: An accelerator for Sphinx speech recognition

The ability to naturally interact with devices is becoming increasingly important. Speech recognition is one well-known solution to provide easy, hands-free user-device interaction. However, speech recognition has significant computation and memory bandwidth requirements, making it challenging to of...

Full description

Saved in:
Bibliographic Details
Main Authors: Chun, A., Chang, J. X., Zhen Fang, Iyer, R., Deisher, M.
Format: Conference Proceeding
Language:English
Subjects:
Engines
Hardware
hardware accelerators
Hidden Markov models
Random access memory
Software
Speech
Speech recognition
Sphinx
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The ability to naturally interact with devices is becoming increasingly important. Speech recognition is one well-known solution to provide easy, hands-free user-device interaction. However, speech recognition has significant computation and memory bandwidth requirements, making it challenging to offer at high performance, real-time and ultra-low power for handheld devices. In this paper, we present a speech recognition accelerator called ISIS. We show the overall execution flow of the accelerated speech recognition solution along with optimizations and the key metrics of performance, area and power.
DOI:10.1109/SASP.2011.5941078