Synthetic F0 can effectively convey speaker ID in delexicalized speech

Eric Morley, Esther Klabbers, Jan Van Santen, Alexander Kain, Seyed Hamidreza Mohammadi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

We investigate the extent to which F0 can convey speaker ID in the absence of spectral, segmental, and durational information. We propose two methods of F0 synthesis based on the Linear Alignment Model (LAM) [2]: one parametric, the other corpus-based. Through a perceptual experiment, we show that F0 alone is able to convey information about speaker ID. We find that F0 synthesized with either LAM-based method conveys speaker ID almost as effectively as natural F0.

Original languageEnglish (US)
Title of host publication13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012
Pages434-437
Number of pages4
Volume1
StatePublished - 2012
Event13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012 - Portland, OR, United States
Duration: Sep 9 2012Sep 13 2012

Other

Other13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012
CountryUnited States
CityPortland, OR
Period9/9/129/13/12

Fingerprint

experiment
Experiments

Keywords

  • F
  • Prosody
  • Recombinant synthesis
  • Speaker identity
  • Speech synthesis

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Communication

Cite this

Morley, E., Klabbers, E., Van Santen, J., Kain, A., & Mohammadi, S. H. (2012). Synthetic F0 can effectively convey speaker ID in delexicalized speech. In 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012 (Vol. 1, pp. 434-437)

Synthetic F0 can effectively convey speaker ID in delexicalized speech. / Morley, Eric; Klabbers, Esther; Van Santen, Jan; Kain, Alexander; Mohammadi, Seyed Hamidreza.

13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012. Vol. 1 2012. p. 434-437.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Morley, E, Klabbers, E, Van Santen, J, Kain, A & Mohammadi, SH 2012, Synthetic F0 can effectively convey speaker ID in delexicalized speech. in 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012. vol. 1, pp. 434-437, 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012, Portland, OR, United States, 9/9/12.
Morley E, Klabbers E, Van Santen J, Kain A, Mohammadi SH. Synthetic F0 can effectively convey speaker ID in delexicalized speech. In 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012. Vol. 1. 2012. p. 434-437
Morley, Eric ; Klabbers, Esther ; Van Santen, Jan ; Kain, Alexander ; Mohammadi, Seyed Hamidreza. / Synthetic F0 can effectively convey speaker ID in delexicalized speech. 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012. Vol. 1 2012. pp. 434-437
@inproceedings{b71c71813efe423eaef690bcd702add1,
title = "Synthetic F0 can effectively convey speaker ID in delexicalized speech",
abstract = "We investigate the extent to which F0 can convey speaker ID in the absence of spectral, segmental, and durational information. We propose two methods of F0 synthesis based on the Linear Alignment Model (LAM) [2]: one parametric, the other corpus-based. Through a perceptual experiment, we show that F0 alone is able to convey information about speaker ID. We find that F0 synthesized with either LAM-based method conveys speaker ID almost as effectively as natural F0.",
keywords = "F, Prosody, Recombinant synthesis, Speaker identity, Speech synthesis",
author = "Eric Morley and Esther Klabbers and {Van Santen}, Jan and Alexander Kain and Mohammadi, {Seyed Hamidreza}",
year = "2012",
language = "English (US)",
isbn = "9781622767595",
volume = "1",
pages = "434--437",
booktitle = "13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012",

}

TY - GEN

T1 - Synthetic F0 can effectively convey speaker ID in delexicalized speech

AU - Morley, Eric

AU - Klabbers, Esther

AU - Van Santen, Jan

AU - Kain, Alexander

AU - Mohammadi, Seyed Hamidreza

PY - 2012

Y1 - 2012

N2 - We investigate the extent to which F0 can convey speaker ID in the absence of spectral, segmental, and durational information. We propose two methods of F0 synthesis based on the Linear Alignment Model (LAM) [2]: one parametric, the other corpus-based. Through a perceptual experiment, we show that F0 alone is able to convey information about speaker ID. We find that F0 synthesized with either LAM-based method conveys speaker ID almost as effectively as natural F0.

AB - We investigate the extent to which F0 can convey speaker ID in the absence of spectral, segmental, and durational information. We propose two methods of F0 synthesis based on the Linear Alignment Model (LAM) [2]: one parametric, the other corpus-based. Through a perceptual experiment, we show that F0 alone is able to convey information about speaker ID. We find that F0 synthesized with either LAM-based method conveys speaker ID almost as effectively as natural F0.

KW - F

KW - Prosody

KW - Recombinant synthesis

KW - Speaker identity

KW - Speech synthesis

UR - http://www.scopus.com/inward/record.url?scp=84878384415&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878384415&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781622767595

VL - 1

SP - 434

EP - 437

BT - 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012

ER -