(30) Foreign Application Priority Data
Mar. 24, 2006 (JP) ............................... .. 2006-081853
(51) Int. Cl.
G10L 15/00 (2006.01)
G10L 17/00 (2006.01)
G10L 21/00 (2006.01)
(52) U.S. Cl. ....................... .. 704/206; 704/241; 704/250
(58) Field of Classification Search ................ .. 704/206,
704/250
See application file for complete search history. (56) References Cited
4,720,863 A 1/1988 Li et al. 5,095,508 A 3/1992 Fujimoto et al. 5,583,961 A 12/1996 Pawlewski et al.
JP 03-266898 A 11/1991
JP 2003-177787 A 6/2003
TW 546633 B 8/2003
OTHER PUBLICATIONS
Notice of Rejection mailed Mar. 23, 2010, for JP Application No.
2006-081853, with English Translation, four pages.
Taiwan Search Report completed Mar. 5, 2010, for TW Application
No. 096109552, received by Foreign Associate Suzuki International
May 27, 2010, two pages.
Kazama, M., et al., Talker Identification Using Narrow-Band Enve-
lope Correlation Matrix, Institute of Electronics, Information and
Communication Engineers, Mar. 2002.
Li, K.-P. and Hughes, G.W., Talker Differences as They Appear In
Correlation Matrices of Continuous Speech Spectra, J . Acoust. Soc.
Am., Apr. 1974, vol. 55—No. 4.
Primary Examiner — Justin W Rider
(74) Attorney, Agent, or Firm — Morrison & Foerster LLP
A similarity degree estimation method is perfonned by two processes. In a first process, an inter-band correlation matrix is created from spectral data of an input voice such that the spectral data are divided into a plurality of discrete bands which are separated from each other with spaces therebetvveen along a frequency axis, a plurality of envelope components of the spectral data are obtained from the plurality of the discrete bands, and elements of the inter-band correlation matrix are correlation values between the respective envelope components of the input voice. In a second process, a degree of similarity is calculated between a pair of input voices to be compared with each other by using respective inter-band correlation matrices obtained for the pair of the input voices through the inter-band correlation matrix creation process.
9 Claims, 9 Drawing Sheets
lst 2nd 3rd 4th Nth
BAND BAND BAND BAND """ " BAND
