Speaker normalization using constrained spectra shifts in audito

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

395 214, G10L 506

Patent

active

056968787

ABSTRACT:
A speaker normalization method is described based on spectral shifts in the auditory filter domain. The method is characterized by using an estimated vocal tract length as a criterion to determine the spectral shift value. Certain constraints are found to be necessary for the shift in the auditory filter domain, and two techniques based on these constraints, the One-Bark shift and the refined Bark-scale shift, are introduced. When tested in vowel classification experiments, significant performance improvement was obtained for both techniques. The method is useful for speaker normalization in speaker-independent speech recognition.

REFERENCES:
patent: 4087632 (1978-05-01), Hofer
patent: 4827516 (1989-05-01), Tsukahara et al.
patent: 4885790 (1989-12-01), McAulay et al.
patent: 5054085 (1991-10-01), Meisel et al.
patent: 5165008 (1992-11-01), Hermansky et al.
patent: 5253326 (1993-10-01), Yong
Analysis and Generation of Voice Template Based on Shift Invariance of BArk Spectral Envelope Tseng et al./IEEE, Aug. 1990.
The effective Second Formant F2' and the Vocal Tract Front-Cavity Hermansky et al./IEEE, 1989.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Speaker normalization using constrained spectra shifts in audito does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Speaker normalization using constrained spectra shifts in audito, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speaker normalization using constrained spectra shifts in audito will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-1614761

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.