<?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">Duffner_Idiap-RR-37-2010/IDIAP</subfield>
		</datafield>
		<datafield tag="245" ind1=" " ind2=" ">
			<subfield code="a">The TA2 Database - A Multi-Modal Database from Home Entertainment</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Duffner, Stefan</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Motlicek, Petr</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Korchagin, Danil</subfield>
		</datafield>
		<datafield tag="856" ind1="4" ind2="0">
			<subfield code="i">EXTERNAL</subfield>
			<subfield code="u">http://publications.idiap.ch/attachments/reports/2011/Duffner_Idiap-RR-37-2010.pdf</subfield>
			<subfield code="x">PUBLIC</subfield>
		</datafield>
		<datafield tag="088" ind1=" " ind2=" ">
			<subfield code="a">Idiap-RR-37-2010</subfield>
		</datafield>
		<datafield tag="260" ind1=" " ind2=" ">
			<subfield code="c">2010</subfield>
			<subfield code="b">Idiap</subfield>
			<subfield code="a">Rue Marconi 19, CH-1920 Martigny</subfield>
		</datafield>
		<datafield tag="771" ind1="2" ind2=" ">
			<subfield code="d">October 2010</subfield>
		</datafield>
		<datafield tag="520" ind1=" " ind2=" ">
			<subfield code="a">This paper presents a new database containing high-definition audio and video recordings in a rather unconstrained video-conferencing-like environment. The database consists of recordings of people sitting around a table in two separate rooms communicating and playing online games with each other. Extensive annotation of head positions, voice activity and word transcription has been performed on the dataset, making it especially useful for evaluating automatic speech-recognition, voice activity detection, speaker localisation, multi-face detection and tracking, and other audio-visual analysis algorithms.</subfield>
		</datafield>
	</record>
</collection>