Interpretation terminals and method for interpretation through communication between interpretation terminals

• US 8,798,985 B2
• Filed: 06/02/2011
• Issued: 08/05/2014
• Est. Priority Date: 06/03/2010
• Status: Active Grant

• Current Assignee: Electronics and Telecommunications Research Institute
• Original Assignee: Electronics and Telecommunications Research Institute
• Inventors: Yun, Seung, Kim, Sanghun
• Primary Examiner(s): Godbold, Douglas
• Assistant Examiner(s): Villena, Mark
• Application Number:
  US13/151,648
• Publication Number:
  US 20110301936A1
• Time in Patent Office: 1,160 Days
• Field of Search: 704/3, 704/226, 704/277, 704/233
• 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 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A method for interpreting a dialogue between two terminals includes establishing a communication channel between interpretation terminals of two parties in response to an interpretation request; specifying a language of an initiating party and a language of the other party in each of the interpretation terminals of the two parties by exchanging information about the language of the initiating party used in the interpretation terminal of the initiating party and the language of the other party used in the interpretation terminal of the other party via the communication channel; recognizing speech uttered from the interpretation terminal of the initiating party; translating the speech recognized by the interpretation terminal of the initiating party into the language of the other party; and transmitting a sentence translated into the language of the other party to the interpretation terminal of the other party.

Claims

1. A mobile interpretation terminal of an initiating party, comprising:

a network interface configured to communicate with a mobile interpretation terminal of an other party;

a speech recognizer configured to recognize an uttered sentence from a speech signal of the initiating party;

a translation module configured to translate the sentence recognized by the speech recognizer into an interpretation language; and

a controller configured to specify the interpretation language and to instruct the network interface to transmit the translated sentence to the interpretation terminal of the other party,

wherein the speech recognizer is configured to detect noise from the speech signal of the initiating party, and to perform speech recognition on the speech signal from which the noise is removed, and

wherein the speech recognizer is configured to compare the speech signal mixed with the noise from the initiating party with a noise signal transmitted from the interpretation terminal of the other party to detect a matching portion between the speech signal and the noise signal as the noise.

2. The interpretation terminal of claim 1, wherein the network interface is configured to perform communication with the interpretation terminal of the other party via a wireless local area network (WLAN), via a mobile communication network, or via near field communications (NFC).

3. The interpretation terminal of claim 2, wherein the WLAN comprises wireless-fidelity (Wi-Fi).

4. The interpretation terminal of claim 1, wherein, upon request for interpretation of a conversation with the other party, the network interface is configured to establish a communication channel with the interpretation terminal of the other party to exchange information required for the establishment with the interpretation terminal of the other party.

5. The interpretation terminal of claim 1, wherein the controller is configured to instruct the network interface to transmit unifying information defining an interpretation range between the two parties to the interpretation terminal of the other party.

6. The interpretation terminal of claim 5, wherein the unifying information defines a place and situation where the interpretation is performed.

7. The interpretation terminal of claim 1, further comprising:

a speech synthesizer configured to synthesize the translated sentence and output the synthesized sentence as voice.

8. The interpretation terminal of claim 7, wherein the pitch of the synthesized sentence output by the speech synthesizer is set to be proportional to a signal-to-noise ratio (SNR) between the noise signal transmitted from the interpretation terminal of the other party and the speech signal of the initiating party.

9. The interpretation terminal of claim 1, wherein the speech recognizer is configured to employ a dialog model to analyze the translated sentence, predict a next dialogue to be uttered based on the analysis result, and utilize the predicted dialog information in the recognition of speech to be uttered next.

10. A method performed by a mobile interpretation terminal of an initiating party for communicating with a mobile interpretation terminal of an other party, the method comprising:

establishing a communication channel with the interpretation terminal of the other party in response to an interpretation request;

specifying an interpretation language of the other party by receiving information about the interpretation language from the interpretation terminal of the other party via the communication channel;

recognizing an uttered sentence from a speech signal of the initiating party;

translating the sentence recognized by the interpretation terminal of the initiating party into the interpretation language of the other party; and

transmitting the translated sentence to the interpretation terminal of the other party,

wherein the recognizing the uttered sentence comprises;

performing synchronization with the interpretation terminal of the other party;

detecting noise from the speech signal of the initiating party; and

performing speech recognition on the speech signal from which the noise is removed, and

wherein the detecting the noise from the speech signal of the initiating party comprises;

comparing the speech signal mixed with the noise from the initiating party with a noise signal transmitted from the interpretation terminal of the other party; and

detecting a matching portion between the speech signal and the noise signal as the noise.

11. The method of claim 10, wherein the communication channel is established through a wireless local area network (WLAN), a mobile communication network, or via near field communications (NFC).

12. The method of claim 11, wherein the WLAN comprises wireless-fidelity (Wi-Fi).

13. The method of claim 10, further comprising:

performing speech synthesis on the translated sentence and outputting the synthesized sentence as voice.

14. The method of claim 10, further comprising:

transmitting unifying information defining an interpretation range between the two parties to the interpretation terminal of the other party.

15. The method of claim 14, wherein the unifying information defines a place and situation where the interpretation is performed.