Speech converting device, speech converting method, program, and medium

• US 20020120436A1
• Filed: 01/24/2002
• Published: 08/29/2002
• Est. Priority Date: 01/24/2001
• Status: Active Grant

• Current Assignee: Panasonic Intellectual Property Corporation of America (Panasonic Holdings Corporation)
• Original Assignee: Matsushita Electric Industrial Company Limited (Panasonic Holdings Corporation)
• Inventors: Mizutani, Kenji, Hirose, Yoshifumi, Maekawa, Hidetsugu, Yoshizawa, Shinichi, Wakita, Yumi
• Granted Patent: US 7,050,979 B2
• Time in Patent Office: Days
• US Class Current: 704/2
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G10L 15/005 Language recognition
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A speech interpreting device which can be easily carried and operated is configured by: a speech inputting/outputting device 102; an image outputting device 103; one or more buttons 106; an image instructing device 105; a computation controlling device 101 which converts phonetically and linguistically data of the source language that are input by the user, and which supplies the converted data to the speech inputting/outputting device 102 and the image outputting device 103; an external large-scale nonvolatile memory device 104 which holds programs for instructing the computation controlling device 101 on procedures of the processes, and data; an external data input/output terminal 107 through which the computation controlling device 101 exchanges programs and data with external apparatuses; and a power source device 108 which supplies a necessary electric power.

Claims

1. A speech converting device comprising:

speech inputting means of inputting speech of a first language;

speech recognizing means of recognizing said input speech;

first extracting/displaying means of extracting and displaying one or plural word strings of said first language, said word strings corresponding to a result of said speech recognition;

conversion object selecting means of, from said displayed word strings, selecting a word string which is expected to become an object of conversion to a second language;

second extracting/displaying means of, when a whole or a part of said selected word string is specified, extracting and displaying candidates of a term which corresponds to contents of said specified whole or part of said selected word string;

candidate selecting means of selecting one of said displayed candidates; and

converting means of determining said object of conversion to said second language on the basis of said selected word string and said selected candidate, and of converting said determined conversion object to a speech language of said second language.

2. A speech converting device according to claim 1, wherein said first extracting/displaying means has a displaying section comprising a display screen which displays said plural word strings that are objects of said selection, and said selected word in respective predetermined regions, and

said second extracting/displaying means overlapingly displays said candidates of a term in a partial region of said display screen in a window form.

3. A speech converting device according to claim 2, wherein, when said selected word string is displayed on said display screen, said first extracting/displaying means additionally displays also information indicating that candidates of the corresponding term can be displayed, with respect to a part of said word string.

4. A speech converting device according to claim 3, wherein said speech converting device further comprises screen display specifying means of specifying said part of said word string on said display screen, said additional information being displayed with respect to said part of said word string.

5. A speech converting device according to claim 1, wherein said converting means determines a result in which said specified part of said word string is replaced with a term of said selected candidate, as said conversion object.

7. A program for causing a computer to function as a whole or a part of said speech recognizing means, said first extracting/displaying means, said conversion object selecting means, said second extracting/displaying means, said candidate selecting means, and said converting means of said speech converting device according to any one of claims 1 to 5.

9. A medium which carries said program according to claim 7, and which is processable by a computer.

6. A speech converting method comprising:

a speech inputting step of inputting speech of a first language;

a speech recognizing step of recognizing said input speech;

a first extracting/displaying step of extracting and displaying one or plural word strings of said first language, said word strings corresponding to a result of said speech recognition;

a conversion object selecting step of, from said displayed word strings, selecting a word string which is expected to become an object of conversion to a second language;

a second extracting/displaying step of, when a whole or a part of said selected word string is specified, extracting and displaying candidates of a term which corresponds to contents of said specified whole or part of said selected word string;

a candidate selecting step of selecting one of said displayed candidates; and

a converting step of determining said object of conversion to said second language on the basis of said selected word string and said selected candidate, and of converting said determined conversion object to a speech language of said second language.

8. A program for causing a computer to function as a whole or a part of said speech recognizing step said first extracting/displaying step, said conversion object selecting step, said second extracting/displaying step, said candidate selecting step, and said converting step of said speech converting method according to claim 6.

10. A medium which carries said program according to claim 8, and which is processable by a computer.