Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Reexamination Certificate
1999-07-19
2003-02-18
Chawan, Vijay (Department: 2654)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
C704S231000, C704S270000, C704S260000, C704S275000
Reexamination Certificate
active
06523004
ABSTRACT:
CROSS REFERENCE TO RELATED APPLICATIONS
(Not Applicable)
STATEMENT REGARDING FEDERALLY SPONSORED RESEARCH OR DEVELOPMENT
(Not Applicable)
BACKGROUND OF THE INVENTION
1. Technical Field
This invention relates to the field of speech recognition software and more particularly to list based natural discourse applications, wherein a user audibly selects an element from a list.
2. Description of the Related Art
Speech recognition software has a wide variety of uses. One important area where this technology has proved to be very useful is the conversion of spoken utterances into selection criteria for selecting an element from a list. List based natural discourse software provides a user with the ability to audibly select an element from a list of elements by uttering selection criteria into a microphone. In a speech-only interface (i.e. no other input, such as from a mouse or keyboard), this selection process can be extremely annoying to a user if it isn't handled properly. For example, long lists, or lists having a plurality of similar or ambiguous elements which meet the selection criteria, can take a long time or multiple iterations with the user to pare the list down to the desired element. Software developers often have to create specialized software code specific to the elements in a list to handle these situations.
SUMMARY OF THE INVENTION
The invention provides a method of selecting an element from a list of elements in a computer system having a list based natural discourse application adapted for speech recognition. In response to a first user element request, the system searches a list of elements to generate a list of matches which contain elements satisfying the element request criteria, and then chooses a preferred method of presenting the matches to a user.
In another aspect of the invention, the system determines the most probable matches, and if the number of matches selected for read out is less than a predetermined number, reads them out. If the number of most probable matches is not less than the predetermined number, the system reads out the number of matches in the list of matches, and then parses the matches into common levels based upon a predetermined criteria.
In yet another aspect of the present invention, the system calculates the time required to read out the match list common levels, the time required to read out all matches, and the time required to iteratively query the user as to which matches of one of the common levels to read out. The system then reads out the match list elements or levels using the method having the lowest calculated time.
In still another aspect of the invention, if the read out method selected selects a level in which the matches are to be read out, the system repeats the steps of the natural discourse application method beginning with calculating the time for each readout method using a revised list of matches containing only match list elements within the selected level until a match list element is selected by the user.
According to another aspect of the invention, if the calculated times are greater than a predetermined number, then after the times are calculated, the system queries the user to select one of the read out methods, and then reads out the matches using the read out method selected by the user. For the convenience of the user, if the user fails to select a read out method, then after the user has affirmatively declined to select a read out method, or fails to respond within a predetermined time, the system may select one of the read out methods based upon the number of match list common levels and the calculated read out times. The present invention accomplishes the general objective of disambiguating a list of elements for speech interfaces by efficiently paring the list down to the desired element.
According to yet another aspect, the invention may be embodied in a computer system having a list based natural discourse application adapted for speech recognition. In that case, the system includes application programming responsive to a first user element request for searching a list of elements to generate a list of matches which contain elements which satisfy the user element request, and then chooses a preferred method for presenting the matches to a user.
Finally, the invention may take the form of a machine readable storage having stored thereon a computer program having a plurality of code sections executable by a machine for causing the machine to perform a set of steps including: in response to a first user element request, searching a list of elements to generate a list of matches which contain elements which satisfy said element request; and choosing a preferred method for presenting the matches to a user.
These and still other objects and advantages of the present invention will be apparent from the description which follows. In the detailed description below, preferred embodiments of the invention will be described in reference to the accompanying drawings. These embodiments do not represent the full scope of the invention. Rather the invention may be employed in other embodiments. Reference should therefore be made to the claims herein for interpreting the breadth of the invention.
REFERENCES:
patent: 5493606 (1996-02-01), Osder et al.
patent: 5774859 (1998-06-01), Houser et al.
patent: 5774860 (1998-06-01), Bayya et al.
patent: 5920836 (1999-07-01), Gould et al.
patent: 6035275 (2000-03-01), Brode et al.
patent: 6073097 (2000-06-01), Gould et al.
patent: 6173266 (2001-02-01), Marx et al.
Sarukkai et al., (“Phonetic set indexing for fast lexical access”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Jan. 1998, vol.20, issue 1, pp. 78-82), teach an indexing key for retrieving a short-list of word possibilities.
Loring Keith P.
Vanbuskirk Ronald E.
Wang Huifang
Akerman & Senterfitt
Chawan Vijay
LandOfFree
Method and apparatus for disambiguating lists of elements... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus for disambiguating lists of elements..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for disambiguating lists of elements... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3175813