Integration of MKL-based and I-vector-based speaker verification by short utterances

Hideitsu Hino, Tetsuji Ogawa

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

We developed a speaker verification system that is efficient for short utterances. The i-vector-based speaker representation has helped realize highly accurate speaker verification systems, however, it might be not robust against short utterances because the reliability of statistics required for extracting i-vectors is low. On the other hand, multiple kernel learning based on conditional entropy minimization has also achieved high accuracy in speaker verification that is robust against intra-speaker variability. To improve the robustness of speaker verification systems against short utterances, we attempted to integrate the above-mentioned complementary systems. Our experimental results showed that the proposed system integration achieved high-accuracy speaker verification systems, irrespective of the utterance lengths, even for very short utterances (e.g., less than two seconds).

Original languageEnglish
Pages562-566
Number of pages5
DOIs
Publication statusPublished - 2013 Jan 1
Event2013 2nd IAPR Asian Conference on Pattern Recognition, ACPR 2013 - Naha, Okinawa, Japan
Duration: 2013 Nov 52013 Nov 8

Conference

Conference2013 2nd IAPR Asian Conference on Pattern Recognition, ACPR 2013
CountryJapan
CityNaha, Okinawa
Period13/11/513/11/8

    Fingerprint

Keywords

  • I-vector
  • Multiple kernel learning
  • Speaker verification

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Hino, H., & Ogawa, T. (2013). Integration of MKL-based and I-vector-based speaker verification by short utterances. 562-566. Paper presented at 2013 2nd IAPR Asian Conference on Pattern Recognition, ACPR 2013, Naha, Okinawa, Japan. https://doi.org/10.1109/ACPR.2013.42