<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>7098</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>196</pageFirst>
    <pageLast>202</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>TUDpress</publisherName>
    <publisherPlace>Dresden</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Listener-Oriented Consequences of Predictability-Based Acoustic Adjustment</title>
    <abstract language="eng">This paper investigated whether predictability-based adjustments in production have listener-oriented consequences in perception. By manipulating the acoustic features of a target syllable in different predictability contexts in German, we tested 40 listeners’ perceptual preference for the manipulation. Four source words underwent acoustic modifications on the target syllable. Our results revealed a general preference for the original (unmodified) version over the modified one. However, listeners generally favored the unmodified version more when the source word had a higher predictable context compared to a less predictable one. The results showed that predictability-based adjustments have perceptual consequences and that listeners have predictability-based expectations in perception.</abstract>
    <parentTitle language="deu">Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. März 2024</parentTitle>
    <identifier type="isbn">978-3-95908-325-6</identifier>
    <identifier type="doi">10.35096/othr/pub-7098</identifier>
    <identifier type="urn">urn:nbn:de:bvb:898-opus4-70984</identifier>
    <enrichment key="OtherSeries">Studientexte zur Sprachkommunikation ; 107</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Omnia Ibrahim</author>
    <author>Ivan Yuen</author>
    <author>Wei Xue</author>
    <author>Bistra Andreeva</author>
    <author>Bernd Möbius</author>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
    <thesisPublisher>Ostbayerische Technische Hochschule Regensburg</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-oth-regensburg/files/7098/essv2024_196.pdf</file>
  </doc>
  <doc>
    <id>7079</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>46</pageFirst>
    <pageLast>53</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>TUDpress</publisherName>
    <publisherPlace>Dresden</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Perception of Formant Distortion in German Words and Non-words</title>
    <abstract language="eng">Concatenative text-to-speech (TTS) systems remain a widely used cheaper alternative to neural TTS systems. Yet concatenation of prerecorded units entails some drawbacks, such as spectral distortion, the perceptual consequences of which remain unclear. In an attempt to bridge this gap, our study focused on the effect of spectral distortion in vowel formants on perceived speech quality in&#13;
naturally-read manipulated German words as well as non-words. More specifically, we explored the distortion effect on a varying number of affected formants, at different magnitude and directionality in two corner vowels /a:/ and /i:/. The results indicate that single formant manipulations have a less pronounced effect on the listeners’ perception compared to multiple formant perturbations. The threshold at which the distortion became generally audible was estimated to lie between 0.4 and 1.0 bandwidth. The directionality of the distortion was not found to be significant.</abstract>
    <parentTitle language="deu">Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. März 2024</parentTitle>
    <identifier type="doi">10.35096/othr/pub-7079</identifier>
    <identifier type="urn">urn:nbn:de:bvb:898-opus4-70793</identifier>
    <identifier type="isbn">978-3-95908-325-6</identifier>
    <enrichment key="OtherSeries">Studientexte zur Sprachkommunikation ; 107</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Uliana Eliseeva</author>
    <author>Ivan Yuen</author>
    <author>Bernd Möbius</author>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
    <thesisPublisher>Ostbayerische Technische Hochschule Regensburg</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-oth-regensburg/files/7079/essv2024_046.pdf</file>
  </doc>
</export-example>
