Speech synthesis

Details Speech synthesis Speech synthesis

1987-11-19

1990-03-13

Wong, Peter S.

Electrical audio signal processing systems and devices

Monitoring/measuring of audio devices

Loudspeaker operation

381 38, G10L 502

Patent

active

049088670

ABSTRACT:
Coded text is converted to phonetic data to drive a synthesis filter. Accent data are also obtained to derive a pitch contour for a variable pitch excitation source. Recognition of the beginning of a paragraph causes a pitch contour of higher pitch than the pitch at a later part of the paragraph. The initial pitch falls following each subgroup into which phrases are divided. Accents within a phrase are assigned pitch values which are high for the first accent, less high for the last; and the remainder alternate between higher and lower lesser values. Accents on repeated words may be suppressed.

REFERENCES:
patent: 3704345 (1972-11-01), Coker et al.
patent: 4344148 (1982-08-01), Brantingham et al.
"Review of Text-to-Speech Conversion for English"; Journal of the Acoustic Society of America, vol. 82, #3, Sep. 1987, pp. 761-762, 767, 769.
"Intonation in Text-to-Speech Synthesis: Evaluation of Algorithms"; Journal of the Acoustical Society of America, vol. 77, #6, Jun. 1987, pp. 2158-2159.
Synthesizing Intonation by Janet Pierrehumbert-Bell Laboratories, Murray Hill, N.J., 07074, accepted for publication 8 Jun. 1981.
J. Accoust. Soc. Am. 70(4), vol. 70, No. 4, Oct. 1981, 99, 985-995.
Intonational Invariance under Changes in Pitch Range and Length-by Mark Liberman and Janet Pierrehumbert-pp. 157-233.
A study of the perception of sentence intonation-Evidence from Danish-Nina G. Thorsen-J. Acous. Soc. Am. 67(3), Mar. 1980, pp. 1014-1030.

Affiliated with

Also associated with

Rating

Speech synthesis does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Speech synthesis, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech synthesis will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-56339