<?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">Garner_SPECOM_2011/IDIAP</subfield>
		</datafield>
		<datafield tag="245" ind1=" " ind2=" ">
			<subfield code="a">Cepstral normalisation and the signal to noise ratio spectrum in automatic speech recognition</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Garner, Philip N.</subfield>
		</datafield>
		<datafield tag="856" ind1="4" ind2="0">
			<subfield code="i">EXTERNAL</subfield>
			<subfield code="u">http://publications.idiap.ch/attachments/papers/2011/Garner_SPECOM_2011.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/Garner_Idiap-RR-15-2011</subfield>
			<subfield code="z">Related documents</subfield>
		</datafield>
		<datafield tag="773" ind1=" " ind2=" ">
			<subfield code="p">Speech Communication</subfield>
			<subfield code="v">53</subfield>
			<subfield code="n">8</subfield>
			<subfield code="c">991--1001</subfield>
		</datafield>
		<datafield tag="260" ind1=" " ind2=" ">
			<subfield code="c">2011</subfield>
		</datafield>
		<datafield tag="024" ind1="7" ind2=" ">
			<subfield code="a">http://dx.doi.org/10.1016/j.specom.2011.05.007</subfield>
			<subfield code="2">doi</subfield>
		</datafield>
		<datafield tag="520" ind1=" " ind2=" ">
			<subfield code="a">Cepstral normalisation in automatic speech recognition is
  investigated in the context of robustness to additive noise.  In
  this paper, it is argued that such normalisation leads naturally to
  a speech feature based on signal to noise ratio rather than absolute
  energy (or power).  Explicit calculation of this SNR-cepstrum
  by means of a noise estimate is shown to have theoretical and
  practical advantages over the usual (energy based) cepstrum.  The
  relationship between the SNR-cepstrum and the articulation index,
  known in psycho-acoustics, is discussed.  Experiments are presented
  suggesting that the combination of the SNR-cepstrum with the well
  known perceptual linear prediction method can be beneficial in noisy
  environments.</subfield>
		</datafield>
	</record>
	<record>
		<datafield tag="980" ind1=" " ind2=" ">
			<subfield code="a">REPORT</subfield>
		</datafield>
		<datafield tag="970" ind1=" " ind2=" ">
			<subfield code="a">Garner_Idiap-RR-15-2011/IDIAP</subfield>
		</datafield>
		<datafield tag="245" ind1=" " ind2=" ">
			<subfield code="a">Cepstral normalisation and the signal to noise ratio spectrum in automatic speech recognition.</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Garner, Philip N.</subfield>
		</datafield>
		<datafield tag="653" ind1="1" ind2=" ">
			<subfield code="a">aurora</subfield>
		</datafield>
		<datafield tag="653" ind1="1" ind2=" ">
			<subfield code="a">Automatic Speech Recognition</subfield>
		</datafield>
		<datafield tag="653" ind1="1" ind2=" ">
			<subfield code="a">cepstral normalisation</subfield>
		</datafield>
		<datafield tag="653" ind1="1" ind2=" ">
			<subfield code="a">Noise Robustness</subfield>
		</datafield>
		<datafield tag="856" ind1="4" ind2="0">
			<subfield code="i">EXTERNAL</subfield>
			<subfield code="u">http://publications.idiap.ch/attachments/reports/2010/Garner_Idiap-RR-15-2011.pdf</subfield>
			<subfield code="x">PUBLIC</subfield>
		</datafield>
		<datafield tag="088" ind1=" " ind2=" ">
			<subfield code="a">Idiap-RR-15-2011</subfield>
		</datafield>
		<datafield tag="260" ind1=" " ind2=" ">
			<subfield code="c">2011</subfield>
			<subfield code="b">Idiap</subfield>
		</datafield>
		<datafield tag="771" ind1="2" ind2=" ">
			<subfield code="d">May 2011</subfield>
		</datafield>
		<datafield tag="520" ind1=" " ind2=" ">
			<subfield code="a">Cepstral normalisation in automatic speech recognition is
  investigated in the context of robustness to additive noise.  It is
  argued that such normalisation leads naturally to a speech feature
  based on signal to noise ratio rather than absolute energy (or
  power).  Explicit calculation of this {\em SNR-cepstrum} by means of a
  noise estimate is shown to have theoretical and practical advantages
  over the usual (energy based) cepstrum.  The SNR-cepstrum is shown
  to be almost identical to the articulation index known in
  psycho-acoustics.  Combination of the SNR-cepstrum with the well
  known perceptual linear prediction method is shown to be beneficial
  in noisy environments.</subfield>
		</datafield>
	</record>
</collection>