Blind Source Separation of Speech in Hardware
Citation:
Niall Hurley, Naomi Harte, Conor Fearon, Scott Rickard `Blind source separation of speech in hardware? in proceedings of the Workshop on Signal Processing Systems, Nov 2005, IEEE, pp 442- 445Download Item:
Blind source separation of speech in hardware.pdf (published (publisher copy) peer-reviewed) 223.5Kb
Abstract:
This paper presents preliminary work on a hardware
implementation of a source separation algorithm employing
time-frequency masking methods. DUET (Degenerate Unmixing
Estimation Technique) has previously been shown to achieve
excellent source separation in real time in software. The current
work is a move towards a hardware realization of DUET that
will allow integration of the algorithm into consumer devices.
Initial stages involve investigating the performance of DUET
when implemented in fixed-point arithmetic and a consideration
of algorithmic changes to make DUET more amenable to
implementation on a DSP processor. Performance is compared
for floating-point and fixed-point implementations. A Weighted
K-means clustering algorithm is presented as an alternative to
gradient descent methods for peak tracking and demonstrated
to achieve excellent performance without adversely affecting
computational load. Preliminary performance figures are given
for an implementation on a TMS320VC5510 DSK.
Sponsor
Grant Number
Enterprise Ireland
Author's Homepage:
http://people.tcd.ie/nharteDescription:
PUBLISHED
Author: HARTE, NAOMI
Publisher:
IEEEType of material:
Conference PaperAvailability:
Full text availableKeywords:
Electronic & Electrical EngineeringLicences: