Method and apparatus for automatically completing text input using speech recognition

• US 20090055174A1
• Filed: 12/21/2007
• Published: 02/26/2009
• Est. Priority Date: 08/20/2007
• Status: Active Grant

• Current Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Han, Ick-sang, Kim, Ji-yeun, Song, Yoon-kyung, Kwak, Byung-kwan, Kim, Nam-hoon, Cho, Joong-mi
• Granted Patent: US 7,970,612 B2
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G06F 3/0233 Character input methods
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 1/72436 for text messaging, e.g. short messaging services [SMS] or e-mails
• CPC Class Codes: H04M 2250/70 methods for entering alphabetical characters, e.g. multi-tap or dictionary disambiguation
• CPC Class Codes: H04M 2250/74 with voice recognition means

Abstract

Provided are a method and apparatus for automatically completing a text input using speech recognition. The method includes: receiving a first part of a text from a user through a text input device; recognizing a speech of the user, which corresponds to the text; and completing a remaining part of the text based on the first part of the text and the recognized speech. Therefore, accuracy of the text input and convenience of the speech recognition can be ensured, and a non-input part of the text can be easily input based on the input part of the text and the recognized speech at a high speed.

Claims

1. A method of automatically completing a text input, the method comprising:

receiving a first part of a text from a user through a text input device;

recognizing a speech of the user, which corresponds to the text; and

completing a remaining part of the text based on the first part of the text and the recognized speech.

2. The method of claim 1, wherein the completion of the remaining part of the text comprises:

generating a plurality of candidates for a non-input part of the text based on the first part of the text and the recognized speech; and

determining the non-input part of the text from one of the candidates selected by the user among the plurality of candidates.

3. The method of claim 1, wherein the completion of the remaining part of the text comprises:

generating a plurality of candidates for a non-input part of the text based on the first part of the text and the recognized speech;

receiving an additional text from the user on recognizing the generated candidates; and

completing the remaining part of the text based on the input first part of the text, the recognized speech, and the additional text.

4. The method of claim 1, wherein the completion of the remaining part of the text comprises:

recognizing an additional speech of the user with respect to a part of the text that corresponds to the speech of the user; and

completing the remaining part of the text based on the input first part of the text and the additionally recognized speech.

5. The method of claim 1, wherein the recognition of the speech comprises:

applying a weighted value to each of a plurality of words forming the input first part of the text in proportion to an input order of the words; and

recognizing the speech in consideration of the weighted values applied to the words.

6. A computer readable recording medium having embodied thereon a computer program for executing the method according to one of claims 1 through 5.

7. An apparatus for automatically completing a text input, the apparatus comprising:

a text input unit receiving a first part of a text from a user through a text input device;

a speech recognition unit recognizing a speech of the user, which corresponds to the text; and

an auto completion unit completing a remaining part of the text based on the input first part of the text and the recognized speech.

8. The apparatus of claim 7, wherein the auto completion unit generates a plurality of candidates for a non-input part of the text based on the input first part of the text and the recognized speech, and determines the non-input part based on one of the candidates selected by the user among the plurality of candidates.

9. The apparatus of claim 7, wherein the auto completion unit generates a plurality of candidates for a non-input part of the text based on the input first part of the text and the recognized speech, receives an additional text from the user who recognizes the generated candidates, and completes the remaining part of the text based on the input first part of the text, the recognized speech, and the additional text.

10. The apparatus of claim 7, wherein the auto completion unit recognizes an additional speech of the user with respect to a part of the text corresponding to the speech of the user, and completes the remaining part of the text based on the input first part of the text and the additionally recognized speech.

11. The apparatus of claim 7, wherein the speech recognition unit applies a weighted value to each of a plurality of words forming the input first part of the text in proportion to an input order of the words, and recognizes the speech in consideration of the weighted values of the words.