<?xml version="1.0" encoding="UTF-8"?>
<collection xmlns="http://www.loc.gov/MARC21/slim">
	<record>
		<datafield tag="980" ind1=" " ind2=" ">
			<subfield code="a">REPORT</subfield>
		</datafield>
		<datafield tag="970" ind1=" " ind2=" ">
			<subfield code="a">Korchagin_Idiap-RR-39-2009/IDIAP</subfield>
		</datafield>
		<datafield tag="245" ind1=" " ind2=" ">
			<subfield code="a">Automatic Temporal Alignment of AV Data</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Korchagin, Danil</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Garner, Philip N.</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Dines, John</subfield>
		</datafield>
		<datafield tag="653" ind1="1" ind2=" ">
			<subfield code="a">audio processing</subfield>
		</datafield>
		<datafield tag="653" ind1="1" ind2=" ">
			<subfield code="a">temporal alignment</subfield>
		</datafield>
		<datafield tag="653" ind1="1" ind2=" ">
			<subfield code="a">time-frequency analysis</subfield>
		</datafield>
		<datafield tag="856" ind1="4" ind2="0">
			<subfield code="i">EXTERNAL</subfield>
			<subfield code="u">http://publications.idiap.ch/attachments/reports/2009/Korchagin_Idiap-RR-39-2009.pdf</subfield>
			<subfield code="x">PUBLIC</subfield>
		</datafield>
		<datafield tag="088" ind1=" " ind2=" ">
			<subfield code="a">Idiap-RR-39-2009</subfield>
		</datafield>
		<datafield tag="260" ind1=" " ind2=" ">
			<subfield code="c">2009</subfield>
			<subfield code="b">Idiap</subfield>
		</datafield>
		<datafield tag="771" ind1="2" ind2=" ">
			<subfield code="d">December 2009</subfield>
		</datafield>
		<datafield tag="520" ind1=" " ind2=" ">
			<subfield code="a">In this paper, we describe the automatic audio-based temporal alignment of audio-visual data, recorded by different cameras, camcorders or mobile phones during social events like high school concerts. All recorded data is temporally aligned with a common master track, recorded by a reference camera. The core of the algorithm is based on perceptual time-frequency analysis with a precision of 10 ms. The results show correct alignment in 99% of cases for a real life dataset.</subfield>
		</datafield>
	</record>
</collection>