DTIC ADA036324: Optimum Speech Classification and Its pdf

DTIC ADA036324: Optimum Speech Classification and Its

More Book Details

Description of the Book:

The problem of determining whether a given interval of a speech signal should be classified as voiced speech, unvoiced speech or silence is formulated as a test of statistical hypotheses. A robust detector is obtained by modelling the speech and the acoustic background noise signals as correlated Gaussian random processes. The methods of statistical decision theory are applied to these models to synthesize an optimum, minimum probability of error, classifier. The optimum classifier is an estimator-correlator receiver which is well approximated using a linear phase high pass filter in the unvoiced channel and a linear phase low pass filter in the voiced channel. A clutter filter appears in the reference channel which tries to eliminate as much noise as possible before forming the unvoiced and voiced correlations. The statistics of the noise are learned during the silent intervals which makes the classifier adaptive to time-varying noise statistics

• Creator/s: Defense Technical Information Center
• Date: 11/9/1976
• Year: 1976
• Book Topics/Themes: DTIC Archive, McAulay, Robert J, MASSACHUSETTS INST OF TECH LEXINGTON LINCOLN LAB, *SIGNAL PROCESSING, *SPEECH RECOGNITION, *ADAPTIVE FILTERS, *VOICE COMMUNICATIONS, *CORRELATORS, ALGORITHMS, CLUTTER, SIGNAL TO NOISE RATIO, MATHEMATICAL FILTERS, DECISION THEORY, CLASSIFICATION, SPEECH TRANSMISSION, HIGH PASS FILTERS, LOW PASS FILTERS, INTELLIGIBILITY, QUIET, VOCODERS, SOUND PITCH

An excerpt captured from the PDF book