Change search
ReferencesLink to record
Permanent link

Direct link
Speaker verification with elicited speaking styles in the VeriVox project
KTH, Superseded Departments, Speech, Music and Hearing.
Show others and affiliations
2000 (English)In: Speech Communication, ISSN 0167-6393, Vol. 31, no 03-feb, 121-129 p.Article in journal (Refereed) Published
Abstract [en]

Some experiments have been carried out to study and compensate for within-speaker variations in speaker verification. To induce speaker variation, a speaking behaviour elicitation software package has been developed. A 50-speaker database with voluntary and involuntary speech variation has been recorded using this software. The database has been used for acoustic analysis as well as for automatic speaker verification (ASV) tests. The voluntary speech variations are used to form an enrolment set for the ASV system. This set is called structured training and is compared to neutral training where only normal speech is used. Both sets contain the same number of utterances. It is found that the ASV system improves its performance when testing on a mixed speaking style test without decreasing the performance of the tests with normal speech.

Place, publisher, year, edition, pages
2000. Vol. 31, no 03-feb, 121-129 p.
Keyword [en]
speaker verification, speaker variation, stressed speech, speech
URN: urn:nbn:se:kth:diva-19855ISI: 000087887100005OAI: diva2:338547
QC 20100525Available from: 2010-08-10 Created: 2010-08-10Bibliographically approved

Open Access in DiVA

No full text

Search in DiVA

By author/editor
Karlsson, Inger A.
By organisation
Speech, Music and Hearing
In the same journal
Speech Communication

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 17 hits
ReferencesLink to record
Permanent link

Direct link