

Type of Document Dissertation Author Berg, Brian LaRoy URN etd-08172001-164442 Title Investigating Speaker Features From Very Short Speech Records Degree PhD Department Electrical and Computer Engineering Advisory Committee
Advisor Name Title A. A. (Louis) Beex Committee Chair Hugh F. VanLandingham Committee Member Ira Jacobs Committee Member Jeffrey H. Reed Committee Member Joe Ball Committee Member Keywords
- Digital Signal Processing
- Speech Analysis
- Speech Synthesis
- Speaker Recognition
- Speaker Identity Verification
- Speech Processing
Date of Defense 2001-07-23 Availability unrestricted Abstract A procedure is presented that is capable of extractingvarious speaker features, and is of particular value for analyzing
records containing single words and shorter segments of speech.
By taking advantage of the fast convergence properties of adaptive
filtering, the approach is capable of modeling the
nonstationarities due to both the vocal tract and vocal cord dynamics.
Specifically, the procedure extracts the vocal tract estimate from within
the closed glottis interval and uses it to obtain a time-domain glottal
signal. This procedure is quite simple, requires minimal manual
intervention (in cases of inadequate pitch detection),
and is particularly unique because it derives both the vocal tract and
glottal signal estimates directly from the time-varying filter
coefficients rather than from the prediction error signal. Using this
procedure, several glottal signals are derived from human and
synthesized speech and are analyzed to demonstrate the glottal
waveform modeling performance and kind of glottal characteristics obtained
therewith. Finally, the procedure is evaluated using automatic speaker
identity verification.
Files
Filename Size Approximate Download Time (Hours:Minutes:Seconds)
28.8 Modem 56K Modem ISDN (64 Kb) ISDN (128 Kb) Higher-speed Access afrif_berg.pdf 10.31 Mb 00:47:45 00:24:33 00:21:29 00:10:44 00:00:55
If you have questions or technical problems, please Contact DLA.