Central Institute for the Deaf

James D Miller

Hisao M Chang

Allard Jongman

Speech processing apparatus and methods utilizing a circuit for electronically deriving from speech over time a series of coordinate values representing positions of points on a path in a mathematical space which path positions represent the speech. An electronic memory prestores phonetic representations in correspondence with indicia of a glide in the path which indicia represent a nucleus in the space at which the glide begins and a range of directions of offglide on the path from the nucleus. A trajectory parameter is electronically computed from the series of coordinate values. When both the trajectory parameter satisfies a predetermined condition for significance and a coordinate value currently reached by the speech is within a predetermined region of such values, a signal is produced. The speech on the path is electronically analyzed in response to the signal for occurrence of a position in the nucleus and an offglide in said range of directions which offglide happens before another significant trajectory parameter occurs. Upon occurrence of such indicia of a glide, the phonetic representation corresponding to the glide indicia is obtained from the electronic memory. Other apparatus and methods for producing a segmentation index signal representing the trajectory parameter are disclosed.

Speech processing apparatus and methods

Speech processing apparatus including a memory for holding prestored information indicative of different phonetic representations corresponding to respective sets of addresses in the memory. Circuitry in the apparatus electrically derives a series of coordinate values of points on a path in a mathematical space from frequency spectra of the speech occurring in successive time intervals respectively, identifies coordinate values approximating at least one position along the path of a peak in magnitude of acceleration, generates a memory address as a function of the position coordinate values and obtains from the memory the phonetic representation information prestored at that memory address. Methods and other apparatus for speech processing are also disclosed.

Speech processing apparatus including an electronic memory and circuitry that derives from speech sets of digital values representative of frequency spectra. The spectra have peaks at frequencies associated therewith. The peaks include a highest magnitude peak for each spectrum. The circuitry also generates an auditory state signal representing the presence or absence of a burst-friction auditory state of the speech. Circuitry further electronically identifies, when the auditory state signal indicates the presence of a burst-friction auditory state, the highest magnitude peak for each spectrum as well as each peak having a magnitude within a range of magnitudes less than the magnitude of the highest magnitude peak, and selectively stores in distinct locations in the memory, respectively representative of normally occurring prominences of a burst-friction sound, the values of frequency of the lowest two frequencies associated with the identified peaks. Other speech processing apparatus and methods are also disclosed.

Growing community of inventors

St. Louis, MO, United States of America

James D Miller