JAIST Repository >
School of Information Science >
Articles >
Journal Articles >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/5030

Title: Spectral stability based event localizing temporal decomposition
Authors: Nandasena, A. C. R.
Nguyen, P. C.
Akagi, M.
Issue Date: 2001-10
Publisher: Academic Press (Elsevier)
Magazine name: Computer Speech & Language
Volume: 15
Number: 4
Start page: 381
End page: 401
DOI: 10.1006/csla.2001.0173
Abstract: In this paper a new approach to Temporal Decomposition (TD) of speech, called Spectral Stability Based Event Localizing Temporal Decomposition(S^2BEL-TD), is presented. The original method of TD proposed by Atal (1983) is known to have the drawbacks of high computational cost, and the high parameter sensitivity of the number and locations of events. In S^2BEL-TD, the event localization is performed based on a maximum spectral stability criterion. This overcomes the high parameter sensitivity of events of Atal's method. Also, S^2BEL-TD avoids the use of the computationally costly singular value decomposition routine used in the Atal's method, thus resulting in a computationally simpler algorithm for TD. Simulation results show that an average spectral distortion of about 1.5 dB can be achieved with line spectral frequencies as the spectral parameter. It is shown that the temporal pattern of the speech excitation parameters can also be well described using the S^2BEL-TD technique.
Rights: NOTICE: This is the author's version of a work accepted for publication by Academic Press (Elsevier). A. C. R. Nandasena, P. C. Nguyen and M. Akagi, Computer Speech & Language, 15(4), 2001, 381-401, http://dx.doi.org/10.1006/csla.2001.0173
URI: http://hdl.handle.net/10119/5030
Material Type: author
Appears in Collections:b10-1. 雑誌掲載論文 (Journal Articles)

Files in This Item:

File Description SizeFormat
C1319.pdf449KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.

 


Contact : Library Information Section, Japan Advanced Institute of Science and Technology