Summary: 1
Phase­Based Dual­Microphone Robust Speech
Enhancement
Parham Aarabi, Member, IEEE, Guangji Shi
The Edward S. Rogers Sr. Department of Electrical and Computer Engineering
University of Toronto, Toronto, Ontario, Canada.
parham@ecf.utoronto.ca
Abstract--- A dual­microphone speech signal enhancement
algorithm, utilizing phase­error based filters that depend
only on the phase of the signals, is proposed. This al­
gorithm involves obtaining time­varying (or alternatively,
time­frequency (TF)) phase­error filters based on prior
knowledge regarding the Time Di#erence of Arrival (TDOA)
of the speech source of interest and the phases of the sig­
nals recorded by the microphones. It is shown that by
masking the TF representation of the speech signals, the
noise components are distorted beyond recognition while
the speech source of interest maintains its perceptual qual­
ity. This is supported by digit recognition experiments
which show a substantial recognition accuracy rate improve­

Source: Aarabi, Parham - Department of Electrical and Computer Engineering, University of Toronto

Collections: Computer Technologies and Information Sciences