ccdhlmrwz02b - Power Consumption of Customized Numerical...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
Power Consumption of Customized Numerical Representations for Audio Signal Processing Roger Chamberlain, Yen Hsiang Chew, Varuna DeAlwis, Eric Hemmeter, John Lockwood, Robert Morley, Ed Richter, Jason White, Huakai Zhang Roger Chamberlain, Yen Hsiang Chew, Varuna DeAlwis, Eric Hemmeter, John Lockwood, Robert Morley, Ed Richter, Jason White, and Huakai Zhang, “Power Consumption of Customized Numerical Representations for Audio Signal Processing,” 6th High Performance Embedded Computing Workshop , September 2002. This research is supported in part by NIH grant 1R4-3DC04028-02 through BECS Technology, Inc. and Hearing Emulations, LLC. Roger Chamberlain has an equity stake in these two companies. Washington University Campus Box 1115 One Brookings Dr. St. Louis, MO 63130-4899
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Power Consumption of Customized Numerical Representations for Audio Signal Processing * Roger Chamberlain, Yen Hsiang Chew, Varuna DeAlwis, Eric Hemmeter, John Lockwood, Robert Morley, Ed Richter, Jason White, and Huakai Zhang School of Engineering and Applied Science Washington University, St. Louis, Missouri Abstract One of the major technical issues facing the designers of modern, hand-held, portable, digital systems is the need to minimize the power consumption of the system to prolong battery life. Many of these systems perform signal processing functions on audio signals (e.g., communications systems, hearing aids, MP3 players, etc). As new signal processing techniques are proposed, the computational requirements invariably grow, putting additional pressure on power consumption. In this work, we investigate the use of non-standard numerical representations for processing of audio signals, showing how the power consumption can be lowered for audio signal processing while maintaining (and even improving) overall signal quality. Standard numerical representations used for signal processing applications include fixed-point representations (typically 16 bits) and floating-point representations (either 32- or 64-bit IEEE standard). The choices of representation available to system designers are much more based upon historical
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 3

ccdhlmrwz02b - Power Consumption of Customized Numerical...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online