Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Listener sensitivity to deviating obstruents in WaveNet
Sigmedia Lab, ADAPT Centre, School of Engineering, Trinity College Dublin, Ireland.
KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Tal, musik och hörsel, TMH.ORCID-id: 0000-0001-9327-9482
Sigmedia Lab, ADAPT Centre, School of Engineering, Trinity College Dublin, Ireland.
Sigmedia Lab, ADAPT Centre, School of Engineering, Trinity College Dublin, Ireland.
2023 (engelsk)Inngår i: Interspeech 2023, International Speech Communication Association , 2023, s. 1080-1084Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

This paper investigates the perceptual significance of the deviation in obstruents previously observed in WaveNet vocoders. The study involved presenting stimuli of varying lengths to 128 participants, who were asked to identify whether each stimulus was produced by a human or a machine. The participants' responses were captured using a 2-alternative forced choice task. The study found that while the length of the stimuli did not reliably affect participants' accuracy in the task, the concentration of obstruents did have a significant effect. Participants were consistently more accurate in identifying WaveNet stimuli as machine when the phrases were obstruent-rich. These findings show that the deviation in obstruents reported in WaveNet voices is perceivable by human listeners. The test protocol may be of wider utility in TTS.

sted, utgiver, år, opplag, sider
International Speech Communication Association , 2023. s. 1080-1084
Emneord [en]
distortion, obstruents, perception, TTS evaluation, WaveNet
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-337831DOI: 10.21437/Interspeech.2023-1843Scopus ID: 2-s2.0-85171585188OAI: oai:DiVA.org:kth-337831DiVA, id: diva2:1803491
Konferanse
24th International Speech Communication Association, Interspeech 2023, Dublin, Ireland, Aug 20 2023 - Aug 24 2023
Merknad

QC 20231009

Tilgjengelig fra: 2023-10-09 Laget: 2023-10-09 Sist oppdatert: 2023-10-09bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Person

Edlund, Jens

Søk i DiVA

Av forfatter/redaktør
Edlund, Jens
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 54 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf