Patent
1995-09-08
1998-05-19
MacDonald, Allen R.
395 262, 395 263, 395 266, G10L 500
Patent
active
057547360
ABSTRACT:
The invention aims to make an automatic information system suitable for the input of requests which are spoken as naturally as possible and which are not subject to restrictions about which the user must be informed in advance. To this end, the system and the method are subdivided into several, essentially independently operating segments with unambiguous interfaces. A first segment serves for the recognition of words and outputs a word graph. A second segment forms a concept graph from the word graph in that essentially the word graph is searched only for word sequences wherefrom values for a database enquiry can be derived; such word sequences, or also single words, are replaced by concepts in the concept graph. In a further segment the concepts in the concept graph are bridged and gaps between the concepts are filled. A speech model is taken into account for this operation. A stochastic attributed grammar is used to determine the concepts from the word graph and to determine the meaning of the word sequences in the concepts. Because irrelevant filler words in the spoken request are ignored early on, the computational expenditure is comparatively small despite the freely pronounced requests.
REFERENCES:
patent: 4277644 (1981-07-01), Levinson et al.
patent: 4481593 (1984-11-01), Bahler
patent: 4624008 (1986-11-01), Vensko et al.
patent: 4882757 (1989-11-01), Fisher et al.
patent: 4947438 (1990-08-01), Paeseler
patent: 5005203 (1991-04-01), Ney
Giachin, "Automatic Training of Stochastic Finite-State Language Models for Speech Understanding", Conference Proceedings of ICASSP92, San Francisco, 1992, vol. 1, pp. 1-173 to 1-176.
U.S. Application Serial No. 07/944,554, filed Sep. 14, 1992.
"Method and Apparatus for Recognizing Spoken Words in a Speech Signal", specification of U.S. Application claiming priority to DE 41 30 631 A1 (presently U.S. Application No. 08/526,017).
Pieraccini et al., (Complxity Reduction in a Large Vocabulary Speech Recognizer, ICASSP'91, Jul. 1991, pp. 729-732).
Giachin (Phrase Bigrams for Continuous Speech Recognition, ICASSP'95, May 1995, pp. 225-228).
Chawan Vijay B.
MacDonald Allen R.
Tierney Daniel E.
U.S. Philips Corporation
LandOfFree
System and method for outputting spoken information in response does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for outputting spoken information in response , we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for outputting spoken information in response will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1862221