Mobile communication terminal apparatus having character string editing function by use of speech recognition function

• US 6,745,053 B1
• Filed: 12/16/1999
• Issued: 06/01/2004
• Est. Priority Date: 12/17/1998
• Status: Expired due to Term

• Current Assignee: Lenovo Innovations Ltd Hong Kong (Lenovo Group Ltd.)
• Original Assignee: NEC Corporation
• Inventors: Usami, Shinya
• Primary Examiner(s): Trost, William
• Assistant Examiner(s): ZEWDU, MELESS NMN
• Application Number:
  US09/464,957
• Time in Patent Office: 1,629 Days
• Field of Search: 455/563, 455/564, 455/565, 455/566, 455/567, 455/568, 455/569, 704/275, 704/243, 704/231, 704/246, 704/251, 704/255
• US Class Current: 455/563
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 1/271 controlled by voice recognition
• CPC Class Codes: H04M 1/2748 by matching character strings
• CPC Class Codes: H04M 1/72436 for text messaging, e.g. short messaging services [SMS] or e-mails

Abstract

A mobile communication terminal apparatus includes a display section, a memory section and a control section. The memory stores character strings for speeches. The control section reads out the character strings for a first speech as character string candidates and controls the display section to display the character string candidates. Then, the control section selects one of the character string candidates in response to a selection instruction, and edits the character string corresponding to the selected character string candidate in response to an edit instruction.

Claims

1. A mobile terminal communication apparatus, comprising:

a display section;

a memory which stores character strings, at least two of said character strings being allocated with speech recognition object data which specifies that said at least two character strings are objects of speech recognition and are associated with a first speech; and

a control section which reads out said character strings associated with said first speech as character string candidates based on said speech recognition object data in response to input of said first speech controls said display section to display said character string candidates, selects one of said character string candidates in response to a selection instruction, and edits said character string corresponding to said selected character string candidate in response to an edit instruction,

wherein said control section searches said character string candidates based on said first speech, a selected language input mode out of a plurality of language input modes and on the number of characters in each of said character strings.

2. A mobile terminal communication apparatus according to claim 1, further comprising an input section used to input speeches including said first speech and a second speech,

wherein said control section carries out speech recognition to the inputted speeches to recognize said first speech and said second speech.

3. The mobile terminal communication apparatus according to claim 2, wherein said control section stores said edited character string in said memory in relation to said second speech.

4. The mobile terminal communication apparatus according to claim 2, wherein said memory stores said character strings for speeches in units of folders, and

wherein said control section stores said edited character string in a specific one of said folders in relation to said second speech.

5. The mobile terminal communication apparatus according to claim 2, wherein said memory stores said character strings for speeches in units of folders, and

wherein said control section determines whether an attribute of a specific folder matches to an attribute of said edited character string, and stores said edited character string in said specific folder in relation to said second speech.

6. The mobile terminal communication apparatus according to claim 1, wherein said plurality of input modes are at least two of a kanji/hiragana language mode, a katakana language mode, an alphabetic language mode, and a numeric/symbol language mode.

7. The mobile communication terminal apparatus according to claim 1, wherein said control section reads out one character string which is not allocated with said speech recognition object data, allocates said speech recognition object data to said one character string, and stores said one character string in said memory in association with said first speech.

8. The mobile communication terminal apparatus according to claim 7, wherein said control section edits said one character string based on data input before said storing of said one character string.

9. A mobile terminal communication apparatus comprising:

a display section;

a memory which stores character strings, at least two of said character strings being allocated with speech recognition object data which specifies that said at least two character strings are objects of speech recognition and are associated with a first speech; and

a control section which reads out said character strings associated with said first speech as character string candidates based on said speech recognition object data in response to input of said first speech, controls said display section to display said character string candidates, selects one of said character string candidates in response to a selection instruction, and edits said character string corresponding to said selected character string candidate in response to an edit instruction,

wherein said control section searches said character string candidates based on said first speech and a selected character input mode out of a plurality of character input modes,

wherein said memory stores said character strings for speeches in units of folders, and

wherein said control section further searches said character string candidates based on the number of characters in each of said character strings, controls said display section to display folders associated with said searched character string candidates, selects one of said displayed folders in response to a folder selection instruction, and controls said display section to display said searched character strings contained in said selected folder.

10. A method of editing a stored character string in a mobile communication terminal apparatus, the method comprising:

reading out at least two character strings based on speech recognition object data in response to a first speech as character string candidates, said at least two character strings being allocated with said speech recognition object data which specifies that said at least two character strings are objects of speech recognition and are associated with said first speech;

displaying said character string candidates;

selecting one of said character string candidates in response to a selection instruction; and

editing said character string corresponding to said selected character string candidate in response to an edit instruction,

wherein said reading includes searching said character string candidates based on said first speech and a selected character input mode out of a plurality of character input modes,

wherein said reading includes;

further searching said character string candidates based on the number of characters in each of said character strings;

displaying folders associated with said searched character string candidates; and

selecting one of said displayed folders in response to a folder selection instruction, whereby said searched character strings in said selected folder are displayed.

11. A method of editing a stored character string in a mobile communication terminal apparatus, the method comprising:

reading out at least two character strings based on speech recognition object data in response to a first speech as character string candidates, said at least two character strings being allocated with said speech recognition object data which specifies that said at least two character strings are objects of speech recognition and are associated with said first speech;

displaying said character string candidates;

selecting one of said character string candidates in response to a selection instruction; and

editing said character string corresponding to said selected character string candidate in response to an edit instruction,

wherein said reading includes searching said character string candidates based on said first speech, a selected language input mode out of a plurality of language input modes and on the number of characters in each of said character strings.

12. The method according to claim 11, wherein said reading includes:

carrying out speech recognition to speeches to recognize said first speech and a second speech.

13. The method according to claim 12, further comprising:

storing said edited character string in relation to said second speech.

14. The method according to claim 12, further comprising:

storing said edited character string in a specific one of folders in relation to said second speech, said character strings being stored for speeches in units of folders.

15. The method according to claim 14, wherein storing further includes:

determining whether an attribute of a specific folder matches to an attribute of said edited character string, before said storing.

16. The method according to claim 11, wherein said plurality of input modes are at least two of a kanji/hiragana language mode, a katakana language mode, an alphabetic language mode, and a numeric/symbol language mode.

17. The method according to claim 11, further comprising:

reading out one character string which is not allocated with said speech recognition object data;

allocating said speech recognition object data to said one character string; and

storing said one character string in association with said first speech.

18. The method according to claim 17, further comprising:

editing said one character string based on data input before said storing of said one character string.