Information processing apparatus and data input method

• US 20050131686A1
• Filed: 12/09/2004
• Published: 06/16/2005
• Est. Priority Date: 12/16/2003
• Status: Abandoned Application

• Current Assignee: Canon Ayutthaya Limited (Canon Inc.)
• Original Assignee: Canon Ayutthaya Limited (Canon Inc.)
• Inventors: Yamamoto, Hiroki, Komori, Yasuhiro
• Application Number:
  US11/007,266
• Publication Number:
  US 20050131686A1
• Time in Patent Office: Days
• US Class Current: 704/231
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G10L 15/197 Probabilistic grammars, e.g. word n-grams

Abstract

More comfortable data input is implemented by using speech recognition and a character prediction function in combination. For example, according to a data input method of this invention, character string candidates which follow a character string input by a character string input device are predicted (S402), and the predicted character string candidates are displayed on a display device (S403). Speech recognition is performed for speech input by the speech input device using the character string candidates displayed on the display device as words to be recognized (S411), and a character string serving as the recognition result is confirmed as a character string to be used (S412).

Claims

1. An information processing apparatus comprising:

prediction means for predicting at least one character candidate which follows at least one input character;

display control means for controlling displaying said at least one character candidate predicted by said prediction means;

speech recognition means for performing speech recognition for input speech using said at least one displayed character candidate as a word to be recognized; and

confirmation means for confirming, as at least one character to be used, at least one character serving as a recognition result obtained by the speech recognition means.

2. The apparatus according to claim 1, further comprising

control means for controlling said display control means and speech recognition means to highlight said at least one character serving as the recognition result obtained by the speech recognition means out of said at least one character candidate displayed by said display control means in order to make a user confirm whether the recognition result is correct and perform speech recognition in this state for utterance given again,

wherein said confirmation means confirms, as said at least one character to be used, a recognition result at a time when it is detected that a predetermined button is pressed, under a control of said control means.

3. The apparatus according to claim 1, further comprising

classification means for, if said at least one character candidate predicted by said prediction means includes homophones, classifying said at least one character candidate into a plurality of groups such that the homophones belong to different groups,

wherein said display control means controls displaying said at least one character candidate by the group formed by said classification means.

4. The apparatus according to claim 1, wherein said speech recognition means determines a pronunciation of a word to be recognized on the basis of character prediction data used by said prediction means.

5. A data input method in an information processing apparatus, comprising:

a prediction step of predicting at least one character candidate which follows at least one character input by a character input device;

a display control step of controlling displaying said at least one character candidate predicted in the prediction step on a display device;

a speech recognition step of performing speech recognition for speech input by a speech input device using said at least one character candidate displayed on the display device as a word to be recognized; and

a confirmation step of confirming, as at least one character to be used, at least one character serving as a recognition result obtained in the speech recognition step.

6. The method according to claim 5, further comprising

a control step of controlling processes in the display control step and speech recognition step to highlight said at least one character serving as the recognition result obtained in the speech recognition step out of said at least one character candidate displayed on the display device to make a user confirm whether the recognition result is correct and perform speech recognition in this state for utterance given again by the speech input device,

wherein in the confirmation step, a recognition result at a time when it is detected that a predetermined button of the character input device is pressed is confirmed as said at least one character to be used, under a control in the control step.

7. The method according to claim 5, further comprising

a classification step of, if said at least one character candidate predicted in the prediction step includes homophones, classifying said at least one character candidate into a plurality of groups such that the homophones belong to different groups,

wherein in the display control step, said at least one character candidate is displayed on the display device by the group formed in the classification step.

8. The method according to claim 5, wherein in the speech recognition step, a pronunciation of a word to be recognized is determined on the basis of character prediction data used in the prediction step.

9. A program executed by a computer, comprising codes of:

a prediction step of predicting at least one character candidate which follows at least one character input by a character input device;

a display control step of controlling displaying said at least one character candidate predicted in the prediction step on a display device;

a speech recognition step of performing speech recognition for speech input by a speech input device using said at least one character candidate displayed on the display device as a word to be recognized; and

a confirmation step of confirming, as at least one character to be used, at least one character serving as a recognition result obtained in the speech recognition step.

10. A computer-readable storage medium which stores a program defined in claim 9.