On the reduction of concatenation artefacts in diphone synthesis

Esther Klabbers; Raymond Veldhuis

On the reduction of concatenation artefacts in diphone synthesis

Esther Klabbers^*, Raymond Veldhuis

^*Corresponding author for this work

Research output: Contribution to conference › Paper › peer-review

43 Citations (Scopus)

13 Downloads (Pure)

Abstract

One well-known problem with diphone concatenation is the occurrence of audible discontinuities at diphone boundaries, which are most prominent in vowels and semi-vowels. Significant formant jumps at certain boundaries suggest that the problem is of a spectral nature. We have examined this hypothesis by correlating the results of a listening experiment with spectral distances measured across diphone boundaries. The aim is to find a spectral distance measure that best predicts when discontinuities are audible in order to find out how the diphone database can best be extended with context-sensitive diphones. The results show that the Kullback-Leibler measure is the best predictor.

Original language	English
Number of pages	4
Publication status	Published - 1998
Externally published	Yes
Event	5th International Conference on Spoken Language Processing, ICSLP 1998 - Sydney, Australia Duration: 30 Nov 1998 → 4 Dec 1998 Conference number: 5

Conference

Conference	5th International Conference on Spoken Language Processing, ICSLP 1998
Abbreviated title	ICSLP
Country/Territory	Australia
City	Sydney
Period	30/11/98 → 4/12/98

Access to Document

Klabbers1998onFinal published version, 115 KB

Cite this

@conference{107419ee4d48432ebc56a6fd58a1b086,

title = "On the reduction of concatenation artefacts in diphone synthesis",

abstract = "One well-known problem with diphone concatenation is the occurrence of audible discontinuities at diphone boundaries, which are most prominent in vowels and semi-vowels. Significant formant jumps at certain boundaries suggest that the problem is of a spectral nature. We have examined this hypothesis by correlating the results of a listening experiment with spectral distances measured across diphone boundaries. The aim is to find a spectral distance measure that best predicts when discontinuities are audible in order to find out how the diphone database can best be extended with context-sensitive diphones. The results show that the Kullback-Leibler measure is the best predictor.",

author = "Esther Klabbers and Raymond Veldhuis",

note = "Funding Information: The work by Klabbers is part of the Priority Programma Language and Speech Technology (TST), sponsored by NWO (The Netherlands Organization for Scientific Research). Publisher Copyright: {\textcopyright} 1998. 5th International Conference on Spoken Language Processing, ICSLP 1998. All rights reserved.; 5th International Conference on Spoken Language Processing, ICSLP 1998, ICSLP ; Conference date: 30-11-1998 Through 04-12-1998",

year = "1998",

language = "English",

}

TY - CONF

T1 - On the reduction of concatenation artefacts in diphone synthesis

AU - Klabbers, Esther

AU - Veldhuis, Raymond

N1 - Conference code: 5

PY - 1998

Y1 - 1998

N2 - One well-known problem with diphone concatenation is the occurrence of audible discontinuities at diphone boundaries, which are most prominent in vowels and semi-vowels. Significant formant jumps at certain boundaries suggest that the problem is of a spectral nature. We have examined this hypothesis by correlating the results of a listening experiment with spectral distances measured across diphone boundaries. The aim is to find a spectral distance measure that best predicts when discontinuities are audible in order to find out how the diphone database can best be extended with context-sensitive diphones. The results show that the Kullback-Leibler measure is the best predictor.

AB - One well-known problem with diphone concatenation is the occurrence of audible discontinuities at diphone boundaries, which are most prominent in vowels and semi-vowels. Significant formant jumps at certain boundaries suggest that the problem is of a spectral nature. We have examined this hypothesis by correlating the results of a listening experiment with spectral distances measured across diphone boundaries. The aim is to find a spectral distance measure that best predicts when discontinuities are audible in order to find out how the diphone database can best be extended with context-sensitive diphones. The results show that the Kullback-Leibler measure is the best predictor.

UR - http://www.scopus.com/inward/record.url?scp=81155150210&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:81155150210

T2 - 5th International Conference on Spoken Language Processing, ICSLP 1998

Y2 - 30 November 1998 through 4 December 1998

ER -

On the reduction of concatenation artefacts in diphone synthesis

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this