<?xml version="1.0" encoding="UTF-8"?>
<collection xmlns="http://www.loc.gov/MARC21/slim">
	<record>
		<datafield tag="980" ind1=" " ind2=" ">
			<subfield code="a">CONF</subfield>
		</datafield>
		<datafield tag="970" ind1=" " ind2=" ">
			<subfield code="a">vepa_icslp04_p/IDIAP</subfield>
		</datafield>
		<datafield tag="245" ind1=" " ind2=" ">
			<subfield code="a">Subjective Evaluation of Join Cost Functions Used in Unit Selection Speech Synthesis</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Vepa, Jithendra</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">King, Simon</subfield>
		</datafield>
		<datafield tag="856" ind1="4" ind2="0">
			<subfield code="i">EXTERNAL</subfield>
			<subfield code="u">http://publications.idiap.ch/attachments/reports/2004/rr04-26.pdf</subfield>
			<subfield code="x">PUBLIC</subfield>
		</datafield>
		<datafield tag="856" ind1="4" ind2=" ">
			<subfield code="u">http://publications.idiap.ch/index.php/publications/showcite/vepa_icslp04</subfield>
			<subfield code="z">Related documents</subfield>
		</datafield>
		<datafield tag="711" ind1="2" ind2=" ">
			<subfield code="a">Proceedings of ICSLP</subfield>
		</datafield>
		<datafield tag="260" ind1=" " ind2=" ">
			<subfield code="c">2004</subfield>
			<subfield code="a">South Korea</subfield>
		</datafield>
		<datafield tag="500" ind1=" " ind2=" ">
			<subfield code="a">IDIAP-RR 04-26</subfield>
		</datafield>
		<datafield tag="520" ind1=" " ind2=" ">
			<subfield code="a">In our previous papers, we have proposed join cost functions derived from spectral distances, which have good correlations with perceptual scores obtained for a range of concatenation discontinuities. To further validate their ability to predict concatenation discontinuities, we have chosen the best three spectral distances and evaluated them subjectively in a listening test. The unit sequences for synthesis stimuli are obtained from a state-of-the-art unit selection text-to-speech system: rVoice from Rhetorical Systems Ltd. In this paper, we report listeners' preferences for each of the three join cost functions.</subfield>
		</datafield>
	</record>
	<record>
		<datafield tag="980" ind1=" " ind2=" ">
			<subfield code="a">REPORT</subfield>
		</datafield>
		<datafield tag="970" ind1=" " ind2=" ">
			<subfield code="a">vepa_icslp04/IDIAP</subfield>
		</datafield>
		<datafield tag="245" ind1=" " ind2=" ">
			<subfield code="a">Subjective Evaluation of Join Cost Functions Used in Unit Selection Speech Synthesis</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Vepa, Jithendra</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">King, Simon</subfield>
		</datafield>
		<datafield tag="856" ind1="4" ind2="0">
			<subfield code="i">EXTERNAL</subfield>
			<subfield code="u">http://publications.idiap.ch/attachments/reports/2004/rr04-26.pdf</subfield>
			<subfield code="x">PUBLIC</subfield>
		</datafield>
		<datafield tag="088" ind1=" " ind2=" ">
			<subfield code="a">Idiap-RR-26-2004</subfield>
		</datafield>
		<datafield tag="260" ind1=" " ind2=" ">
			<subfield code="c">2004</subfield>
			<subfield code="b">IDIAP</subfield>
		</datafield>
		<datafield tag="520" ind1=" " ind2=" ">
			<subfield code="a">In our previous papers, we have proposed join cost functions derived from spectral distances, which have good correlations with perceptual scores obtained for a range of concatenation discontinuities. To further validate their ability to predict concatenation discontinuities, we have chosen the best three spectral distances and evaluated them subjectively in a listening test. The unit sequences for synthesis stimuli are obtained from a state-of-the-art unit selection text-to-speech system: rVoice from Rhetorical Systems Ltd. In this paper, we report listeners' preferences for each of the three join cost functions.</subfield>
		</datafield>
	</record>
</collection>