Method and system for text editing in hand-held electronic device

• US 20040083109A1
• Filed: 10/29/2002
• Published: 04/29/2004
• Est. Priority Date: 10/29/2002
• Status: Active Grant

• Current Assignee: Nokia Technologies Oy (Nokia Corporation)
• Original Assignee: Nokia Corporation
• Inventors: Sathish, Sailesh, Halonen, Katriina
• Granted Patent: US 7,003,457 B2
• Time in Patent Office: Days
• US Class Current: 704/277
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A dynamically generated small grammar is used for text editing using voice commands in a hand-held electronic device where memory requirements do not allow a large grammar to be used. However, the text is dictated using a large grammar, which can reside in the electronic device or in a remote site. When an editing session begins, words in the dictated text are added to the small grammar. As such, words to be deleted or replaced can be located, for example. When a voice command calls for a text-modifying word, the text-modifying word is obtained from the small grammar if possible. Otherwise it is obtained from the large grammar. During the editing session, as more text-modifying words are used to modify the text, these words are also added to the small grammar. At the end of the editing session, the dynamically generated part of the small grammar is removed.

Claims

1. A method of modifying text (140) in a hand-held electronic device (10) in an editing session, the text including a plurality of third words, wherein at least a part of the text is dictated using a first grammar (130), the first grammar including a plurality of first words, and wherein the hand-held electronic device comprises a second grammar (150) smaller than the first grammar, the second grammar including a plurality of second words for editing purposes, said method characterized by

providing the third words to the second grammar so that the second words include some or all of the third words.

2. The method of claim 1, wherein the second grammar includes a plurality of voice recognizable commands, and at least one of the voice recognizable commands can be activated in order to modify the text, said method characterized in that

when the activated voice recognizable command specifies a text-modifying word for modifying the text,

the text-modifying word is obtained from the second grammar if the text-modifying word is one of the second words, otherwise

the text modifying word is obtained from the first words in the first grammar.

3. The method of claim 2, further characterized by

including in the second grammar the text-modifying word obtained from the first words so that the second words further include said obtained word for further use.

4. The method of claim 1, wherein the second grammar includes a plurality of voice recognizable commands, and at least one of the voice recognizable commands can be activated in order to modify the text, said method characterized in that

the first words comprise a plurality of subsets of words associated with a plurality of classes, and the voice recognizable commands include at least one class command for specifying at least one of the classes, wherein when the activated voice recognizable command includes the class command, the subset of words associated with the class specified in the class command is provided to the second grammar, so as to allow the second words to further include said subset of words.

5. The method of claim 1, wherein the second grammar includes a plurality of voice recognizable commands, and at least one of the voice recognizable commands can be activated in order to modify the text, said method characterized in that

the first words comprise a plurality of subsets of words associated with a plurality of classes, and the voice recognizable commands include a plurality of class commands for specifying the classes, wherein

when the activated voice recognizable command includes one of the class commands, the subset of words associated with the class specified in said one class command is provided to the second grammar so as to allow the second words to further include said subset of words, and

when the activated voice recognizable command further includes a different one of the class commands, a different subset of words associated with the class specified in said one different class command is provided to the second grammar so as to allow the second words to further include said different subset of words.

6. The method of claim 5, further characterized in that

when the activated voice recognizable command further includes the different one of the class commands, said subset of words is removed from the second grammar in order to reduce size of the second grammar.

7. The method of claim 1, wherein the hand-held electronic device (10) is operatively connected to a remote site (20), said method further characterized in that

the first grammar is located in the remote site.

8. The method of claim 7, wherein the second grammar includes a plurality of voice recognizable commands, and at least one of the voice recognizable commands can be activated in order to modify the text, said method characterized in that

the hand-held electronic device (10) further comprises a third grammar (160) including a plurality of subsets of words associated with a plurality of classes, and the voice recognizable commands include at least one class command for specifying at least one word to the classes, wherein when the activated voice recognizable command includes the class command, the subset of words associated with the class in the class command is provided to the second grammar so that the second words further include said subset of words.

9. The method of claim 7, wherein the second grammar includes a plurality of voice recognizable commands, and at least one of the voice recognizable commands can be activated in order to modify the text, said method characterized in that

the hand-held electronic device (10) further comprises a third grammar (160) including a plurality of subsets of words associated with a plurality of classes, and the voice recognizable commands include a plurality of class commands for specifying the classes, wherein

when the activated voice recognizable command includes one of the class commands, the subset of words associated with the class specified in said one class command is provided to the second grammar so that the second words further include said subset of words, and

when the activated voice recognizable command further includes a different one of the class commands, a different subset of words associated with the class specified in said one different class command is provided to the second grammar so that the second words further include said different subset of words.

10. The method of claim 9, further characterized in that

when the activated voice recognizable command further includes the different one of the class commands, said subset of words is removed from the second grammar in order to reduce size of the second grammar.

11. The method of claim 1, wherein the second grammar includes a plurality of voice recognizable commands, and at least one of the voice recognizable commands can be activated in order to modify the text, said method characterized in that

the third words are associated with a plurality of word locations, and

the voice recognizable commands include at least one location command for specifying the word location, wherein

when said at least one activated voice recognizable command includes the location command and identifies at least one of the third words to be replaced, the text-modifying word replaces said at least one identified third word based on the specified word location.

12. The method of claim 2, wherein the second grammar includes a plurality of voice recognizable commands, and at least one of the voice recognizable commands can be activated in order to modify the text, said method characterized in that

the third words are associated with a plurality of word locations, and

the voice recognizable commands include at least one location command for specifying the word location so as to modify the text using the text-modifying word at the specified word location in response to the activated voice recognizable command.

13. The method of claim 1, wherein the second grammar includes a plurality of voice recognizable commands, and at least one of the voice recognizable commands can be activated in order to modify the text, said method characterized in that

the third words are associated with a plurality of word locations, and the voice recognizable commands include at least one location command for specifying the word location so as to delete at least one of the third words at the specified word location in responsive to the activated voice recognizable command.

14. The method of claim 1, comprising the step of terminating the editing session, said method characterized by

removing the third words from the second grammar after said terminating step.

15. The method of claim 3, comprising the step of terminating the editing session, said method characterized by

removing the obtained text-modifying word from the second grammar after said terminating step.

16. The method of claim 4, comprising the step of terminating the editing session, said method characterized by

removing the subset of words from the second grammar after said terminating step.

17. The method of claim 8, comprising the step of terminating the editing session, said method characterized by

removing the subset of words from the second grammar after said terminating step.

18. A hand-held electronic device (10) having modifiable text (140) including a plurality of third words, wherein at least a part of the text is dictated using a first grammar (130), the first grammar including a plurality of first words, said device characterized by:

a voice input module; and

a memory module operatively connected to the voice input module, wherein the memory module comprises;

a second grammar including a plurality of second words and at least one of the third words, the second grammar smaller than the first grammar.

19. The hand-held electronic device of claim 18, wherein the first grammar is included in the memory module.

20. The hand-held electronic device of claim 18, wherein the memory module further comprises a plurality of voice recognizable commands which can be activated via the voice input module for modifying the text, wherein

when the activated voice recognizable command specifies a text-modifying word for modifying the text, the text-modifying word is obtained from the second grammar if the text-modifying word is one of the second words, otherwise the text-modifying word is obtained from the first words in the first grammar.

21. The hand-held electronic device of claim 20, wherein the second words further include the text modifying word obtained from the first words for further use.

22. The hand-held electronic device of claim 20, wherein the first grammar is located in a remote site, the remote site operatively connected to the hand-held electronic device so as to allow the text-modifying word to be obtained from the first words in the first grammar.

23. The hand-held electronic device of claim 22, further comprising a third grammar (160) including a plurality of subsets of words associated with a plurality of classes, wherein

the voice recognizable commands include at least one class command for specifying at least one of the classes, and when

the activated voice recognizable command includes the class command, the subset of words associated with the class specified in the class command is provided to the second grammar so that the second words further include said subset of words.