<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>262</id>
    <completedYear>2014</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>IEEE</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">A Pitch Extraction Algorithm Tuned for Automatic Speech Recognition</title>
    <abstract language="eng">In this paper we present an algorithm that produces pitch and probability-of-voicing estimates for use as features in automatic speech recognition systems. These features give large performance improvements on tonal languages for ASR systems, and even substantial improvements for non-tonal languages. Our method, which we are calling the Kaldi pitch tracker (because we are adding it to the Kaldi ASR toolkit), is a highly modified version of the getf0 (RAPT) algorithm. Unlike the original getf0 we do not make a hard decision whether any given frame is voiced or unvoiced; instead, we assign a pitch even to unvoiced frames while constraining the pitch trajectory to be continuous. Our algorithm also produces a quantity that can be used as a probability of voicing measure; it is based on the normalized autocorrelation measure that our pitch extractor uses. We present results on data from various languages in the BABEL project, and show a large improvement over systems without tonal features and systems where pitch and POV information was obtained from SAcC or getf0.</abstract>
    <parentTitle language="eng">2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, May 2014.</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Pegah Ghahremani</author>
    <author>Bagher BabaAli</author>
    <author>Daniel Povey</author>
    <author>Korbinian Riedhammer</author>
    <author>Jan Trmal</author>
    <author>Sanjeev Khudanpur</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Automatic Speech Recognition</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
</export-example>
