Time series association learning

Details Time series association learning Time series association learning

1990-01-31

1995-08-08

MacDonald, Allen R.

G10L 900

Patent

active

054406617

ABSTRACT:
An acoustic input is recognized from inferred articulatory movements output by a learned relationship between training acoustic waveforms and articulatory movements. The inferred movements are compared with template patterns prepared from training movements when the relationship was learned to regenerate an acoustic recognition. In a preferred embodiment, the acoustic articulatory relationships are learned by a neural network. Subsequent input acoustic patterns then generate the inferred articulatory movements for use with the templates. Articulatory movement data may be supplemented with characteristic acoustic information, e.g. relative power and high frequency data, to improve template recognition.

REFERENCES:
patent: 3383466 (1968-05-01), Hillix et al.
patent: 3610831 (1971-10-01), Moshier et al.
patent: 4087632 (1978-05-01), Hafer
patent: 4426551 (1984-01-01), Komatsu et al.
patent: 4757541 (1988-07-01), Beadles
patent: 4769845 (1988-09-01), Nakamura et al.
patent: 4841575 (1989-06-01), Welsh et al.
patent: 4945494 (1990-07-01), Penz et al.
patent: 4980917 (1990-12-01), Hutchins
Petajan, "Automatic Lipreading to Enhance Speech Recognition", 1985 IEEE, pp. 40-47.
Lippmann, et al., "Neural-Net Classifiers Useful for Speech Recognition," IEEE 1st International Conference on Neural Networks, Jun. 21-24, 1987 pp. IV-417-IV425.
K. Shirai et al., "Phrase Speech Recognition of Large Vocabulary Using Feature in Articulatory Domain," Proceedings IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 2, pp. 26.9.1-26.9.4 (San Diego, Calif. 1984).
S. Ishizaki, "Vowel Discrimination by Use of Articulatory Model," Proceedings of the Fourth International Joint Conference on Pattern Recognition, pp. 1050-1052 (Kyoto, Japan 1978).
J. L. Elman et al., "Learning the Hidden Structure of Speech," 83 J. Acoust. Soc. Am. No. 4, pp. 1615-1626 (Apr. 1988).
C. P. Browman et al., "Towards an Articulatory Phonology," 3 Phonology Yearbook, pp. 219-252 (1986).
D. E. Rumelhart et al., 1 Parallel Distributed Processing, Chapter 8, "Learning Internal Representation by Error Propagation," pp. 318-362, The MIT Press, Cambridge Massachusetts (1986).

Affiliated with

Also associated with

Rating

Time series association learning does not yet have a rating. At this time, there are no reviews or comments for this patent.

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

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-977573