Abstract: A speech is recognized using ACF factors extracted from running autocorrelation functions calculated from the speech. The extracted ACF factors are a W?(0) (width of ACF amplitude around zero-delay origin), a W?(0)max (maximum value of the W?(0)), a ?1 (pitch period), a ?1 (pitch strength), and a ??1/?t (rate of the pitch strength change). Syllables in the speech are identified by comparing the ACF factors with templates stored in a database.
Abstract: A speech is recognized using ACF factors extracted from running autocorrelation functions calculated from the speech. The extracted ACF factors are a W?(0) (width of ACF amplitude around zero-delay origin), a W?(0)max (maximum value of the W?(0)), a ?1 (pitch period), a ?1 (pitch strength), and a ??1/?t (rate of the pitch strength change). Syllables in the speech are identified by comparing the ACF factors with templates stored in a database.