The "SIVA" speech database for speaker verification: description and evaluation

Text Dependent (TD) Speaker Recognition systems assume that the password to be uttered by the speaker is known to the system. As the password is known, the system can apply a password-specific model capturing the speaker dynamics well. This enables TD systems to perform better than textindependent systems. We present a variation of the TD systems, called text-conditioning, in which the password is uniquely chosen by each user. This delivers a higher level of discrimination since the linguistic and phonetic differences of the passwords themselves are exploited in separating the speakers. As the database for such a study was not publicly available, we built an extensive database for speaker recognition having such text-conditioning property. The database is tested with various speaker recognition trials. The results indicate that for the design of a practical TD speakerrecognition system, "text-conditioning" does offer a significant edge.

show abstract

“…Table 1 presents a number of contemporary speaker recognition databases details of which can be found in [1][2][3][4][5][6][7].…”

Section: Overview Of Current Text-dependent Speaker Recognition Databasementioning

confidence: 99%

Usefulness of text-conditioning and a new database for text-dependent speaker recognition research

2008

View full text Add to dashboard Cite

show abstract

“…The Italian speech database SIVA (Speaker Identification and Verification Archives) [18], contains the recordings of more than 2, 000 speakers. This corpus consists of four speaker categories: male users, female users, male impostors and female impostors.…”

Section: Sivamentioning

confidence: 99%

Local Features for Speaker Recognition

Paredes

Vidal

Casacuberta

2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. An approach combining a simple local representation method with a k-nearest neighbors-based direct voting scheme is proposed for speaker recognition. This approach rises computational problems that we effectively solved through an approximate fast k-nearest neighbors search technique. Experimental results with the EuTrans and SIVAspeech databases are reported showing the effectiveness of the proposed approach.

show abstract

Arabic intonatif speech database

Boukadida

Ellouze

2004 IEEE International Conference on Industrial Technology, 2004. IEEE ICIT '04.

View full text Add to dashboard Cite

The "SIVA" speech database for speaker verification: description and evaluation

Cited by 5 publications

References 1 publication

Usefulness of text-conditioning and a new database for text-dependent speaker recognition research

Usefulness of text-conditioning and a new database for text-dependent speaker recognition research

Local Features for Speaker Recognition

Arabic intonatif speech database

Contact Info

Product

Resources

About