Journal article Open Access

Adaptive Refinements of Pitch Tracking and HNR Estimation within a Vocoder for Statistical Parametric Speech Synthesis

Al-Radhi, Mohammed Salah; Csapó, Tamás Gábor; Németh, Géza


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">continuous F0</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">speech synthesis</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">time-warping</subfield>
  </datafield>
  <controlfield tag="005">20211126174227.0</controlfield>
  <datafield tag="500" ind1=" " ind2=" ">
    <subfield code="a">1</subfield>
  </datafield>
  <controlfield tag="001">5729320</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Budapest University of Technology and Economics</subfield>
    <subfield code="0">(orcid)0000-0003-4375-7524</subfield>
    <subfield code="a">Csapó, Tamás Gábor</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Budapest University of Technology and Economics</subfield>
    <subfield code="0">(orcid)0000-0002-2311-4858</subfield>
    <subfield code="a">Németh, Géza</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">3595588</subfield>
    <subfield code="z">md5:8e2b0b3591bc7c49771d98cc56f7acfd</subfield>
    <subfield code="u">https://zenodo.org/record/5729320/files/applsci-09-02460.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2019-06-16</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-ai4eu</subfield>
    <subfield code="o">oai:zenodo.org:5729320</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Budapest University of Technology and Economics</subfield>
    <subfield code="0">(orcid)0000-0003-3094-6916</subfield>
    <subfield code="a">Al-Radhi, Mohammed Salah</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Adaptive Refinements of Pitch Tracking and HNR Estimation within a Vocoder for Statistical Parametric Speech Synthesis</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-ai4eu</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">825619</subfield>
    <subfield code="a">A European AI On Demand Platform and Ecosystem</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;Recent studies in text-to-speech synthesis have shown the benefit of using a continuous pitch estimate; one that interpolates fundamental frequency (F0) even when voicing is not present. However, continuous F0 is still sensitive to additive noise in speech signals and suffers from short-term errors (when it changes rather quickly over time). To alleviate these issues, three adaptive techniques have been developed in this article for achieving a robust and accurate F0: (1) we weight the pitch estimates with state noise covariance using adaptive Kalman-filter framework, (2) we iteratively apply a time axis warping on the input frame signal, (3) we optimize all F0 candidates using an instantaneous-frequency-based approach. Additionally, the second goal of this study is to introduce an extension of a novel continuous-based speech synthesis system (i.e., in which all parameters are continuous). We propose adding a new excitation parameter named Harmonic-to-Noise Ratio (HNR) to the voiced and unvoiced components to indicate the degree of voicing in the excitation and to reduce the influence of buzziness caused by the vocoder. Results based on objective and perceptual tests demonstrate that the voice built with the proposed framework gives state-of-the-art speech synthesis performance while outperforming the previous baseline.&amp;nbsp;&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isCitedBy</subfield>
    <subfield code="a">10.3390/app9122460</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.3390/app9122460</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">article</subfield>
  </datafield>
</record>
19
18
views
downloads
Views 19
Downloads 18
Data volume 64.7 MB
Unique views 15
Unique downloads 15

Share

Cite as