Third International Conference on Spoken Language Processing (ICSLP 94)

Yokohama, Japan
September 18-22, 1994

Speaker Recognition Based on Subspace Methods

Y. Ariki, K. Doi

Ryukoku University, Seta Otsu-shi, Japan

This paper proposes a method to separate speaker information from phonetic information included in speech data. A speaker recognition method using the separated speaker information is also proposed and shown to be equivalent with a method based on speaker subspace. The validity of this proposed method was verified by earring out simple speaker recognition experiments.

Full Paper

Bibliographic reference.  Ariki, Y. / Doi, K. (1994): "Speaker recognition based on subspace methods", In ICSLP-1994, 1859-1862.