Presentation	1994/3/25 Text-Independent Speaker Recognition Utilizing Neural Network Techniques Seiji Ishihara, Takashi Nagano,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	Text-independent speaker recognition techniques is developed by using layerd neural networks of the same number as that of speakers to be recognized.Each network classifies a speaker from the other speakers.Inputs to the networks are the power spectrum of each flame which is obtained by short time spectrum analysis of sound waves.We executed experiments to recognize six speakers by using four texts with different length for both tearning and test. The results showed that texts used for tearning and test require some length in order to obtain good recognition rate.It was also found that there existed bodi effective phonemes and non-effective phonemes for recognition.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Text-Independent Speaker Recognition / Short Time Spectrum Analysis / Layered Neural Net
Paper #	NC93-121
Date of Issue

Conference Information
Committee	NC
Conference Date	1994/3/25(1days)
Place (in Japanese)	(See Japanese page)
Place (in English)
Topics (in Japanese)	(See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To	Neurocomputing (NC)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Text-Independent Speaker Recognition Utilizing Neural Network Techniques
Sub Title (in English)
Keyword(1)	Text-Independent Speaker Recognition
Keyword(2)	Short Time Spectrum Analysis
Keyword(3)	Layered Neural Net
1st Author's Name	Seiji Ishihara
1st Author's Affiliation	College of Engineering,Hosei University()
2nd Author's Name	Takashi Nagano
2nd Author's Affiliation	College of Engineering,Hosei University
Date	1994/3/25
Paper #	NC93-121
Volume (vol)	vol.93
Number (no)	537
Page	pp.pp.-
#Pages	7
Date of Issue