<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>7097</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>188</pageFirst>
    <pageLast>195</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">Evaluating the Impact of Prosody Feature Normalization on the Controllability of Pitch in Speech Synthesis</title>
    <abstract language="eng">Recent neural text-to-speech (TTS) models are able to synthesize highly&#13;
natural speech signals using deep learning techniques. In practical applications, it can be desirable to have explicit control over the prosody (speech rate, fundamental frequency, and energy) of the synthesized speech. Such controllability can be achieved by adding prosody prediction modules, whose main purpose is to estimate plausible prosody features for each phoneme in the text input. This explicit modeling also allows for changing prosody features at inference time, consequently enabling the adjustment of the prosody in the synthesized audio. In this paper, we evaluate to which extent deliberate manipulation of such prosody features is reflected in the resulting speech audio. We focus particularly on changing the pitch (i.e., fundamental frequency) while applying different normalization strategies.</abstract>
    <parentTitle language="deu">Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. März 2024</parentTitle>
    <identifier type="doi">10.35096/othr/pub-7097</identifier>
    <identifier type="urn">urn:nbn:de:bvb:898-opus4-70976</identifier>
    <identifier type="isbn">978-3-95908-325-6</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>Judith Bauer</author>
    <author>Frank Zalkow</author>
    <author>Meinard Müller</author>
    <author>Christian Dittmar</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/7097/essv2024_188.pdf</file>
  </doc>
</export-example>
