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

Hideitsu Hino, Tetsuji Ogawa

研究成果: Paper査読

1 被引用数 (Scopus)

抄録

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).

本文言語English
ページ562-566
ページ数5
DOI
出版ステータスPublished - 2013
イベント2013 2nd IAPR Asian Conference on Pattern Recognition, ACPR 2013 - Naha, Okinawa, Japan
継続期間: 2013 11 52013 11 8

Conference

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

ASJC Scopus subject areas

  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Integration of MKL-based and I-vector-based speaker verification by short utterances」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル