<?xml version="1.0" encoding="UTF-8"?>
<collection xmlns="http://www.loc.gov/MARC21/slim">
	<record>
		<datafield tag="980" ind1=" " ind2=" ">
			<subfield code="a">ARTICLE</subfield>
		</datafield>
		<datafield tag="970" ind1=" " ind2=" ">
			<subfield code="a">Parthasarathi_IJST(SPRINGER)_2011/IDIAP</subfield>
		</datafield>
		<datafield tag="245" ind1=" " ind2=" ">
			<subfield code="a">Robustness of Group Delay Representations for Noisy Speech Signals</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Parthasarathi, Sree Hari Krishnan</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Rajan, Padmanabhan</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Murthy, Hema A</subfield>
		</datafield>
		<datafield tag="856" ind1="4" ind2="0">
			<subfield code="i">EXTERNAL</subfield>
			<subfield code="u">http://publications.idiap.ch/attachments/papers/2011/Parthasarathi_IJST(SPRINGER)_2011.pdf</subfield>
			<subfield code="x">PUBLIC</subfield>
		</datafield>
		<datafield tag="773" ind1=" " ind2=" ">
			<subfield code="p">IJST (Springer)</subfield>
			<subfield code="v">14</subfield>
			<subfield code="n">4</subfield>
		</datafield>
		<datafield tag="260" ind1=" " ind2=" ">
			<subfield code="c">2011</subfield>
		</datafield>
		<datafield tag="520" ind1=" " ind2=" ">
			<subfield code="a">This paper demonstrates the robustness of group delay based features to additive
noise. First, we analytically show the robustness of group delay based represen-
tations. The analysis makes use of the fact that, for minimum-phase signals, the
group delay function can be represented in terms of the cepstral coefficients of
the log-magnitude spectrum. Such a representation results in the speech spectrum
dominating over the noise spectrum, both at low and high SNRs. Further, we ex-
perimentally demonstrate the robustness of the representation on a voice activity
detection (VAD) task, comparing a group delay based VAD algorithm with standard
VAD methods as well as a magnitude-spectrum based method.</subfield>
		</datafield>
	</record>
</collection>