Speech translation device and computer readable medium

• US 7,047,195 B2
• Filed: 01/26/2005
• Issued: 05/16/2006
• Est. Priority Date: 01/07/1999
• Status: Expired due to Term

• Current Assignee: Rakuten Group, Inc.
• Original Assignee: Hitachi, Ltd.
• Inventors: Obuchi, Yasunari, Koizumi, Atsuko, Kitahara, Yoshinori, Kaji, Hiroyuki
• Primary Examiner(s): Knepper, David D.
• Application Number:
  US11/042,147
• Publication Number:
  US 20050131673A1
• Time in Patent Office: 475 Days
• Field of Search: None
• US Class Current: 704/260
• CPC Class Codes: G06F 40/47 Machine-assisted translation, e.g. using translation memory
• CPC Class Codes: G10L 15/10 using distance or distortion measures between unknown speech and reference templates

Abstract

A translation device which has both advantages of a table look-up translation device and advantages of a machine translation device by leading the user'"'"'s utterance through a sentence template suitable for the user'"'"'s intent of speech is realized. Since the translation device searches for sentence templates suitable for the user'"'"'s intent of speech with an orally inputted keyword and displays retrieved sentences, the user'"'"'s utterance can be lead. In addition, the user is free from a troublesome manipulation for replacing a word since an expression uttered by the user is inserted into a replaceable portion (slot) within the sentence template, and the translation device translates a resulting sentence with the replaced expression embedded in the slot.

Claims

1. A method for assisting vocal input, comprising the steps of:

displaying, on a display unit, a template text having at least one replaceable section, phonetic information of said template being stored in a memory;

inputting, through an input unit, a vocal input;

performing a recognition processing, in a calculation unit, wherein said vocal input is compared with said phonetic information of said template to determine a section of said vocal input corresponding to said replaceable section, and said section of said vocal input corresponding to said replaceable section is recognized with reference to words included in a stored dictionary; and

outputting at least the result of said recognition of said section of said vocal input corresponding to said replaceable section.

2. A method for assisting vocal input according to claim 1, wherein said display unit displays a plurality of said template texts, and said calculation unit compares said vocal input with phonetic information of said plurality of templates to determine a template text corresponding to said vocal input.

3. A method for assisting vocal input according to claim 1, wherein said display unit displays information indicating a category of expression for said replaceable section, and said calculation unit performs said recognition of said section of said vocal input corresponding to said replaceable section using phonetic information of expressions corresponding to said category in said stored dictionary.

4. A processing apparatus for receiving vocal input, comprising:

a memory for storing data of at least one template text having at least one replaceable section, and a dictionary for vocal input recognition including phonetic information of expressions;

a display unit for displaying said template text and information about said replaceable section stored in said memory;

an input unit for inputting a vocal input; and

a calculation unit for performing a recognition processing by comparing said vocal input with said phonetic information of said templates to determine a section of said vocal input corresponding to said replaceable section, and recognizing said section of said vocal input corresponding to said replaceable section using words included in said dictionary, and outputting at least the result of said recognition of said section of said vocal input corresponding to said replaceable section.

5. A processing apparatus according to claim 4, wherein said display unit displays a plurality of said template texts, and said calculation unit compares said vocal input with phonetic information of said plurality of templates to determine a template text corresponding to said vocal input.

6. A processing apparatus according to claim 4, wherein said display unit displays information indicating a category of expression for said replaceable section, and said calculation unit performs said recognition of said section of said vocal input corresponding to said replaceable section using expressions corresponding to said category in said stored dictionary.

7. A computer readable recording medium having recorded thereon a program for causing a computer to perform the steps of;

displaying, on a display unit, a template text having at least one replaceable section, phonetic information of said template being stored in a memory;

inputting, through an input unit, a vocal input;

performing a recognition processing, in a calculation unit, wherein said vocal input is compared with said phonetic information of said template to determine a section of said vocal input corresponding to said replaceable section, and said section of said vocal input corresponding to said replaceable section is recognized with reference to a word included in a stored dictionary; and

outputting at least the result of said recognition of said section of said vocal input corresponding to said replaceable section.

8. A computer readable recording medium according to claim 7, wherein said display unit displays a plurality of said template texts, and said calculation unit compares said vocal input with said phonetic information of plurality of said templates to determine a template text corresponding to said vocal input.

9. A computer readable recording medium according to claim 7, wherein said display unit displays information indicating a category of expression for said replaceable section, and said calculation unit performs said recognition of said section of said vocal input corresponding to said replaceable section using expressions corresponding to said category in said stored dictionary.

10. A method for assisting vocal input, comprising the steps of:

displaying, on a display unit, a plurality of template texts, phonetic information of said templates being stored in a memory;

inputting, through an input unit, a vocal input;

performing a recognition processing, in a calculation unit, wherein said vocal input is compared with said phonetic information of said templates to determine a template whose phonetic information indicates a higher similarity with the vocal input than other templates; and

outputting at least the result of said recognition processing.

11. A method for assisting vocal input according to claim 10, wherein said plurality of template texts are selected from a group of template texts stored in said memory based on correspondence with a keyword input before said displaying step.

12. A processing apparatus for receiving vocal input, comprising:

a memory for storing phonetic information of a plurality of templates;

a display unit for displaying at least a part of said template texts;

an input unit for inputting a vocal input; and

calculation unit for performing a recognition processing by comparing said vocal input with said phonetic information of at least a part of said templates to determine a template whose phonetic information indicates a higher similarity with the vocal input than another template text and outputting at least the result of said recognition processing.

13. processing apparatus according to claim 12, wherein at least a part of said plurality of template texts are selected from the stored template texts based on correspondence with a keyword input before said displaying step.

14. A computer readable recording medium having recorded thereon a program for causing a computer to perform the steps of;

displaying, on a display unit, a plurality of template texts, phonetic information of said templates being stored in a memory;

inputting, through an input unit, a vocal input;

performing a recognition processing, in a calculation unit, wherein said vocal input is compared with said phonetic information of said templates to determine a template whose phonetic information indicates a higher similarity with the vocal input than other templates; and

outputting at least the result of said recognition processing.

15. A method for assisting vocal input according to claim 14, wherein said plurality of template texts are selected from a group of template texts stored in said memory based on correspondence with a keyword input before said displaying step.