Word recognition using choice lists

• US 20050043949A1
• Filed: 09/24/2004
• Published: 02/24/2005
• Est. Priority Date: 09/05/2001
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: Voice Signal Technologies Incorporated (Microsoft Corporation)
• Inventors: Roth, Daniel L., Johnston, David F., Cohen, Jordan R., Porter, Edward W.
• Granted Patent: US 7,809,574 B2
• Time in Patent Office: Days
• US Class Current: 704/251
• CPC Class Codes: G10L 15/14 using statistical models, e.g. Hidden Markov Models [HMMs] G10L15/18 takes precedence

Abstract

One aspect of the invention involves word recognition that uses scrollable choice lists in which choices are listed in character-order. Another aspect relates to a scrollable, visually-displayed word recognition choice list, where the recognition candidates on the choice list are each associated with a choice-selecting symbol the user can use to select a desired recognition candidate by pressing an associated button, and where the same choice-selecting symbol is used for different choices displayed on the display at different times as a result of scrolling. Another aspect of the invention relates to providing a choice list of best scoring characters for a particular character position in the spelling of a filter that is used to filter word recognition. Another aspect of the invention relates to a choice list used in word recognition in which the choice list can be scrolled horizontally.

Claims

1. A computerized method of performing word recognition comprising:

receiving a word input signal containing non-textual user input representing a sequence of one or more words;

performing word recognition upon the input signal to produce a choice list of best scoring recognition candidates, each comprised of a sequence of one or more words, found by the recognizer to have the best probability of corresponding to the input signal;

producing user-perceivable output representing a choice list of the best scoring recognition candidates, with the candidates being ordered in said choice list according to a character ordering of the sequence of characters corresponding to the one or more words associated with each candidate in the list;

providing a user interface which enables a user to select one of the character-ordered recognition candidates from the choice list; and

responding to user selection of one of the recognition candidates from the choice list by treating the selected candidate as the one or more words that correspond to the word input signal;

wherein;

said choice list includes more recognition candidates than fit on the display at one time; and

the choice list is scrollable, so that a user can select to scroll the list relative to the display, so as to see more recognition candidates on the list than fit on the display at one time.

2. A method as in claim 1 wherein:

the word recognition selects a single best scoring recognition candidate; and

the single best scoring candidate is placed in a position in said user-perceivable output that is independent of where the character sequence corresponding to the one or more words associated with the single best scoring candidate would, according to said character ordering, fall in the character-ordered list.

3. A method as in claim 1 wherein:

the word input signal is a representation of an utterance of a spoken word; and

the word recognition is speech recognition.

4. A method as in claim 1 wherein the user perceivable output includes showing a character-ordered list of said best scoring recognition candidates on a visual display.

5. A method as in claim 4 wherein:

the character-ordered list is an alphabetically ordered list; and

the display of an individual recognition candidates in the list includes a sequence of one or more alphabetically spelled words.

6. A method as in claim 5 wherein:

said choice list has two alphabetically ordered sub-lists;

the first sub-list includes a alphabetically ordered plurality of the highest scoring choice candidates, which fit on the display at one time; and

the second sub-list includes an alphabetically ordered plurality of other best scoring choice candidates which would not fit on the display at the same time as the first sub-list.

7. A method as in claim 6 wherein the second sub-list has more candidates than fit on the display at one time.

8. A method as in claim 5 further including:

providing a user interface that allows the user to select a filtering sequence of one or more letter-indications after said display of the character-ordered list of best scoring recognition candidates; and

responding to the selection of said filtering sequence by generating and showing on said display a new alphabetized choice list of recognition candidates, which new choice list is limited to candidates whose sequence of one or more characters start with said filtering sequence; and

providing a user interface that enables a user to select one of the alphabetized recognition candidates from the new choice list;

responding to a user selection of one of the recognition candidates in the new choice list by treating the selected candidate as the one or more words that correspond to the word input signal.

9. A method as in claim 8 wherein said responding to the selection of said filtering sequence by generating and showing a new alphabetized choice list includes:

detecting whether or not the number of recognition candidates is below a desired number; and

when a detection is made that the number of recognition candidates is below the desired number, selecting from a vocabulary list one or more additional candidates that start with the filtering sequence for inclusion in said new alphabetized choice list.

10. A method as in claim 8 wherein:

the user interface that allows the user to input said letter-indicating inputs allows the user to enter such inputs by pressing one or more keys of a telephone keypad, with the pressing of a given telephone pad key indicating that a corresponding letter in the sequence of one or more characters associated with a desired recognition candidate is one of a set of multiple letters associated with the given key; and

the new alphabetically ordered candidate list is limited to candidates that start with an initial sequence of letters corresponding to the sequence of letter-indicating inputs, in which each letter of a listed candidate that corresponds to a letter-indicating input entered by pressing a given telephone pad key is one of the set of letters associated with said given key.

11. A method as in claim 8 wherein:

the user interface that allows the use to select a sequence of one or more letter-indications allows a user to select a desired number of characters from the start of a string of alphabetic characters contained within a selected one of the recognition candidates displayed in a choice list; and

said user interface response to such a selection by using the selected one or more characters as all or part of said sequence of one or more letter-indications.

12. A method as in claim 5 further including:

providing a user interface that allows the user to indicate the selection of a location on a displayed alphabetized choice list between two successively listed candidates or between a first or last listed candidate and the beginning or end, respectively, of the list; and

responding to such a selection by redisplaying a new alphabetized choice list limited to recognition candidates having spellings between the two candidates or between the candidates and the beginning or end of the alphabet, respectively.

13. A method as in claim 4 wherein:

the input signal represents the speaking of one or more word for a number that can be represented by a sequence of one or more digits;

said word recognition is speech recognition;

the choice list display each recognition candidate as a sequence of one or more digits; and

the character ordering of the choice list orders recognition candidates based on a numerical ordering of their digit sequences.

14. A method as in claim 13 wherein:

said input signal represents the speaking of a phone number; and

said responding to a user selection of a recognition candidate causes the phone number displayed for the selected recognition candidate to be automatically dialed.

15. A method as in claim 4 wherein:

the input signal represents the speaking of one or more names from contact information;

said word recognition is speech recognition; and

the choice list represents a plurality of best scoring names from the contact information, ordered alphabetically.

16. A method as in claim 4 further including:

providing a user interface that allows a user to select to scroll the visual display of the choice list up or down by multiple recognition candidates; and

responding to such a user selection by moving the choice list up or down relative to the display by multiple recognition candidates.

17. A method as in claim 16 wherein:

the method is performed on a cell phone; and

the display is the display of a cell phone; and

the user interface that allows the user to select to scroll by multiple recognition candidates allows the user to make such a selection by pressing a button on the cell phone.

18. A method as in claim 4 wherein:

the method is performed on a cell phone; and

the display is the display of a cell phone.

19. A method as in claim 18 wherein:

the showing of the choice list on the cell display includes displaying a different number in association with each recognition candidate in the portion of the choice list shown on the display at one time;

providing a user interface which enables a user to select one of the recognition candidates from the choice list by pressing a numbered phone key on said cell phone corresponding to a desired recognition candidate; and

responding to a user selection of one of the recognition candidates from the choice list by treating the selected candidate as the one or more words and/or numbers that correspond to the word input signal.

20. A computerized method of performing word recognition comprising:

receiving a word input signal containing non-textual user input representing a sequence of one or more words;

performing word recognition upon the input signal to produce a choice list of best scoring recognition candidates, each comprised of a sequence of one or more words and/or numbers, found by the recognizer to have a relatively high probability of corresponding to the input signal;

showing the choice list in a user scrollable display, with the choice list having more recognition candidates than fit on the display at one time so that only a sub-portion of the choice list is displayed at one time;

displaying a different symbol in association with each recognition candidate in the portion of the choice list shown on the display at one time, with the same symbol being associated with different recognition candidates shown on the display at different times as a result of the scrolling a given choice list;

responding to user input selecting to scroll the choice list up or down by moving the choice list relative to the display up or down, respectively, so as to change the portion of the choice list shown on the display;

providing a user interface which enables a user to select one of the recognition candidates from the choice list by pressing a button associated with the symbol corresponding to a desired recognition candidate; and

responding to the pressing of a button associated with a symbol corresponding to a given recognition candidate by treating the given candidate as the one or more words and/or numbers that correspond to the word input signal.

21. A method as in claim 20 wherein the word input signal is a representation of the speaking of one or more words and the word recognition is speech recognition.

22. A method as in claim 20 wherein:

said user input selecting to scroll the choice list up or down includes a multiple-candidate scroll input; and

said responding to user input selecting to scroll includes responding to each multiple-candidate scroll input by moving the choice list up or down relative to the display by multiple recognition candidates.

23. A method as in claim 20 wherein:

the method is performed on a cell phone; and

the display is the display of a cell phone.

24. A method as in claim 23 wherein the symbols associated with displayed recognition candidates are numbers and the buttons associated with such symbols are numbered phone keys.

25. A method as in claim 20 wherein:

each recognition candidate has associated with it a character string; and

the recognition candidates in the scrollable choice list are ordered by the character ordering in which their respective character strings occur.

26. A method as in claim 20 wherein the recognition candidates in the scrollable choice list are ordered by their recognition score against the word signal.

27. A method as in claim 20 further including responding to user input selecting to scroll the choice list right or left by moving the choice list relative to the display right or left, respectively, so as to change the portion of individual choices in the choice list that are shown on the display.

28. A method as in claim 27 wherein said responding to user input to scroll the choice list right or left includes responding to such an input by horizontally scrolling the display of individual recognition choices by a greater horizontal distance than the display of said symbol associated with each such recognition choice.

29. A computerized method of performing word recognition comprising:

receiving a word input signal containing non-textual user input representing a sequence of one or more words;

receiving a sequence of one or more filter input signal, each containing non-textual user input representing a sequence of one or more characters;

responding to the one or more filter input signals by producing a filter, representing one or more possible character sequences, each having one or more characters, found to have the best probability of corresponding to the filter input signal;

performing word recognition upon said word input signal, to generating a list of best scoring word recognition candidates, each of which is selected to start with a one of the one or more character sequences represented by the filter;

producing user-perceivable output representing;

said list of best scoring word recognition candidates; and

an indication of the character sequence represented by said filter that corresponds to the initial characters of one of the listed best scoring recognition candidates;

providing a user interface that enables a user to select one of the word recognition candidates from said list and/or to select a filter character from said indication of a character sequence represented by the filter;

responding to selection of one of the word recognition candidates from the choice list by treating the selected candidate as the one or more words that correspond to the word input signal;

responding to selection of a filter character by providing a user perceivable output of a choice list of other characters selected as having the best probability of corresponding to the selected character'"'"'s position in the filter;

enabling a user to choose one of the characters in the character choice list;

responding to a choice of a character in the character choice list by;

limiting the one or more possible character sequences represented by the filter to ones having the chosen character in the selected filter character'"'"'s position; and

repeated said generation of a user-perceivable list of word recognition candidates using the filter as limited by the chosen character.

30. A method as in claim 29 wherein the limiting of the one or more possible character sequences represented by the filter includes limiting such character sequences to ones having the characters, if any, that occur before the selected character in said user-perceivable indication of the character sequence represented by said filter.

31. A method as in claim 29 wherein:

said filter represents only one given character sequence;

said generation of a list of recognition candidates limits the listed word recognition candidates to only those starting with said one given character sequence; and

the user-perceivable indication of the character sequence represented by the filter indicates the characters of said one given character sequence.

32. A method as in claim 29 wherein:

said filter represents a plurality of character sequences;

said generation of a list of word recognition candidates limits the listed word recognition candidates to those starting with one of said plurality of character sequences; and

the user-perceivable indication of the character sequence represented by the filter indicates the characters of one of said plurality of character sequences.

33. A method as in claim 29 wherein:

the filter input signals correspond to a sequence of one or more phone key presses, where each of a plurality of said phone keys has a set of two or more letters associated with it; and

the responding to the one or more filter input signals produces a filter representing a plurality sequences of characters, where each such sequence has a character position associated with each such key press, and where in different one of said character sequences the character position associated with a given key press has a different one of the set of letters associated with the given key press'"'"'s phone key.

34. A method as in claim 29 wherein:

the filter input signals correspond to a sequence of one or more utterances each of a sequence of one or more letter indications; and

the responding to the filter input signals includes performing speech recognition upon the sequence of one or more utterances to produce a filter representing one or more sequences of characters corresponding to the characters recognized from said utterances.

35. A computerized method of performing word recognition comprising:

receiving a word input signal containing non-textual user input representing a sequence of one or more words;

performing word recognition upon the input signal to produce a choice list of best scoring recognition candidates, each comprised of a sequence of one or more words, found by the recognizer to have the best probability of corresponding to the input signal;

showing the choice list in a user scrollable display; and

responding to user input selecting to scroll the choice list right or left by moving the choice list relative to the display right or left, respectively, so as to change the portion of individual choices in the choice list that are shown on the display.

36. A method as in claim 35 wherein said method is practiced on a cell phone and the user input selecting to scroll horizontally is the pressing of a button or key on the cell phone.

37. A method as in claim 35 wherein:

the choice list has more recognition candidates than fit on the display at one time so only a sub-portion of the recognition candidates are displayed at one time;

the method further includes responding to user input selecting to scroll the choice list up or down by moving the choice list relative to the display up or down, respectively, so as to change the sub-set of recognition candidates shown on the display.