Data processing: database and file management or data structures – Database design – Data structure types
Reexamination Certificate
1998-09-02
2002-09-24
Feild, Joseph H. (Department: 2176)
Data processing: database and file management or data structures
Database design
Data structure types
C704S235000, C434S179000
Reexamination Certificate
active
06457031
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
This invention relates generally to the field of speech recognition applications, and in particular, to text marking for deferred correction or review of dictated text in a speech recognition system proofreader.
2. Description of Related Art
A proofreader in a speech recognition system plays both audio and text on a word-by-word basis to facilitate proofreading and correction of a document. As the words are played, the user has the option to halt playback and modify or otherwise correct the portions of interest. However, if numerous corrections need to be made the continual cessation and resumption of playback could quickly become tiresome and frustrating. Accordingly, a user may instead prefer to mark the dictated words for correction or review at a later time so that playback need not be interrupted. There is therefore a long-felt need for an improved method for marking text for later review and possible correction or revision.
SUMMARY OF THE INVENTION
In accordance with the inventive arrangements, a user can mark words in the document while playback continues uninterrupted, can request that marked words be highlighted in the document, can request that marked words not be highlighted in the document, can step through the marked words sequentially, jumping across intervening text, can request that a mark be automatically removed when the word is corrected, and can remove an individual mark.
A method for marking dictated text for deferred correction or review of dictated text in a speech recognition system proofreader, in accordance with the inventive arrangement, comprises the steps of: displaying previously dictated text;
sequentially highlighting words in the text; selectively establishing a mark for different ones of the sequentially highlighted words responsive to user commands; and, storing the marks in an ordered list, each of the marks including a current position and length of a corresponding marked word, whereby the marked words can be later recalled for correction in accordance with the ordered list.
The method can further comprise the step of visually highlighting the marked words responsive to a user request, or the step of automatically visually highlighting the marked words.
The method can further comprise the steps of: displaying the previously dictated text in a first display window; sequentially visually highlighting each word of the previously dictated text in a first manner; and, visually highlighting each marked word in a second manner. In this characterization, the method still further comprises the steps of: sequentially displaying in a second display window portions of the previously dictated text including the word highlighted in the first manner; and, sequentially displaying in a third display window within the second display window the word in the previously dictated text highlighted in the first manner.
In a different characterization, the method can further comprise the steps of: displaying the previously dictated text in a first display window; sequentially displaying in a second display window a portion of the previously dictated text including the sequentially highlighted word; and, sequentially displaying in a third display window within the second display window the sequentially highlighted word. In accordance with this different characterization, the method still further comprises the steps of: temporarily and automatically highlighting each of the sequentially highlighted words; and, visually highlighting the selectively marked words in a different manner.
The method can further comprise the steps of: permanently visually highlighting the selectively marked words in the different manner; and, removing the permanent visual highlighting responsive to a user command. Alternatively, the method can further comprise the steps of: permanently visually highlighting the selectively marked words in the different manner; and, automatically removing the permanent visual highlighting after the marked word has been edited.
Prior to the storing step, the method can comprise the steps of, prior to the storing step: determining the current position of each marked word; and, determining the length of each marked word at each the current position.
The method can further comprise the step of recalling the marked words for correction. The marked words can be selectively played back in forward and reverse sequences corresponding to the ordered list.
The method can further comprise the steps of: examining the ordered list of marks responsive to a user request to show a mark; retrieving text associated with the mark; and, displaying the retrieved text. The displayed text can by visually highlighted.
The method can further comprise the steps of: responsive to a user modifying text by inserting, deleting or replacing characters, determining a number of characters being inserted, deleted or replaced; determining a position where the characters where the characters were inserted, deleted or replaced; if the modifying changed a marked word, adjusting the length of the marked word in the corresponding mark in the ordered list; determining if the modifying was an insertion or deletion; and, if the modifying was an insertion or deletion, adding or subtracting the number of characters to or from positions of all marks in the ordered list following a point of the insertion or deletion. The displaying of the marked words can be refreshed.
The method can further comprise the step of removing marks corresponding to modification of words corresponding to the marks. The marks can be removed automatically or can be selectively removed responsive to user commands.
REFERENCES:
patent: 5712957 (1998-01-01), Waibel et al.
patent: 5819225 (1998-10-01), Eastwood et al.
patent: 5829000 (1998-10-01), Huang et al.
patent: 5850629 (1998-12-01), Holm et al.
patent: 5855000 (1998-12-01), Waibel et al.
patent: 5857099 (1999-01-01), Mitchell et al.
patent: 5864805 (1999-01-01), Chen et al.
patent: 5884258 (1999-03-01), Rozak et al.
patent: 5899976 (1999-05-01), Rozak
patent: 5909667 (1999-06-01), Leontiades et al.
patent: 5920836 (1999-07-01), Gould et al.
patent: 5920837 (1999-07-01), Gould et al.
patent: 5950160 (1999-09-01), Rozak
patent: 5960447 (1999-09-01), Holt et al.
patent: 6064959 (2000-05-01), Young et al.
patent: 6098085 (2000-08-01), Blonder et al.
patent: 6113394 (2000-09-01), Edgar
patent: 6195637 (2001-02-01), Ballard et al.
patent: 6199076 (2001-03-01), Logan et al.
patent: 6212498 (2001-03-01), Sherwood et al.
Lai, Jennifer et al., MedSpeak: report creation with continuous speech recognition, ACM conference proceedings on Human factors in computing systems, pp. 431-438, Mar. 1997.*
Proofreading Aid for Speech Dictation Systems, IBM Technical Disclosure Bullitan, vol. 39, issue 1, pp. 149-150, Jan. 1996.
Akerman & Senterfitt
Bashore William L.
Feild Joseph H.
International Business Machines Corp.
LandOfFree
Method of marking previously dictated text for deferred... 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 of marking previously dictated text for deferred..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of marking previously dictated text for deferred... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2892029