Method, device and system for providing language service

• US 9,128,930 B2
• Filed: 12/08/2014
• Issued: 09/08/2015
• Est. Priority Date: 10/31/2013
• Status: Active Grant

• Current Assignee: Tencent Technology Company Limited (Tencent Holdings Limited)
• Original Assignee: Tencent Technology Company Limited (Tencent Holdings Limited)
• Inventors: Chen, Bo, Lu, Li, Song, Yang, Ye, Hao
• Primary Examiner(s): GUERRA-ERAZO, EDGAR X
• Application Number:
  US14/563,939
• Publication Number:
  US 20150120277A1
• Time in Patent Office: 274 Days
• Field of Search: 704/2, 704/3, 704/4, 704/5, 704/9, 704/10, 704/235, 704/246, 704/270, 704/270.1, 704/275, 704/276
• US Class Current: 1/1
• 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 13/086 Detection of language
• CPC Class Codes: G10L 15/005 Language recognition
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A method, device and system for providing a language service are disclosed. In some embodiments, the method is performed at a computer system having one or more processors and memory for storing programs to be executed by the one or more processors. The method includes receiving a first message from a client device. The method includes determining if the first message is in a first language or a second language different than the first language. The method includes translating the first message into a second message in the second language if the first message is in the first language. The method includes, alternatively, generating a third message in the second language if the first message is in the second language, where the third message includes a conversational response to the first message. The method further includes returning one of the second message and the third message to the client device.

Claims

1. A method, comprising:

at a computer system having one or more processors and memory for storing programs to be executed by the one or more processors;

receiving a first message from a client device;

determining if the first message is in a first language or a second language, the second language being different than the first language;

if the first message is in the first language, translating the first message into a second message in the second language;

if the first message is in the second language, generating a third message in the second language, the third message including a conversational response to the first message; and

returning one of the second message and the third message to the client device,

wherein the first message is a speech message, the second message is a speech message, the translating further including;

generating, based on the first message, a fourth message using a speech recognition system for the first language, the fourth message being a textual message in the first language and a speech-to-text transform of the first message;

translating the fourth message into a fifth message using machine translation, the fifth message being a textual message in the second language; and

generating, based on the fifth message, the second message using speech synthesis, the second message being a text-to-speech transform of the fifth message.

2. The method of claim 1, wherein the first message is a speech message, the determining includes:

calculating a first confidence value for the first message based on an acoustic model associated with the first language;

calculating a second confidence value for the first message based on an acoustic model associated with the second language; and

determining if the first message is in the first language or the second language based on a comparison of the first confidence value and the second confidence value.

3. The method of claim 1, wherein the first message is a speech message, the third message is a speech message, the generating the third message includes:

generating, based on the first message, a fourth message using a speech recognition system for the second language, the fourth message being a textual message in the second language and a speech-to-text transform of the first message;

generating, based on the fourth message, a fifth message using man-machine interrogation, the fifth message being a textual message in the second language and a conversational response to the fourth message; and

generating, based on the fifth message, the third message using speech synthesis, the third message being a text-to-speech transform of the fifth message.

4. A server device, comprising:

one or more processors; and

memory storing one or more programs to be executed by the one or more processors, the one or more programs comprising instructions for;

receiving an indication of an operational mode from a client device, the operational mode being a conversation mode or a translation mode;

receiving a first message from the client device;

determining if the first message is in a first language or a second language, the second language being different than the first language;

if the first message is in the second language and the operational mode is the conversation mode, generating a second message in the second language, the second message including a conversational response to the first message;

if the first message is in the second language and the operational mode is the translation mode, translating the first message into a third message in the first language; and

returning one of the second message and the third message to the client device if the first message is in the second language,

wherein the first message is a speech message, the second message is a speech message, the translating further including;

generating, based on the first message, a fourth message using a speech recognition system for the first language, the fourth message being a textual message in the first language and a speech-to-text transform of the first message;

translating the fourth message into a fifth message using machine translation, the fifth message being a textual message in the second language; and

generating, based on the fifth message, the second message using speech synthesis, the second message being a text-to-speech transform of the fifth message.

5. The server device of claim 4, wherein the one or more programs further comprise instructions for:

if the first message is in the first language and the operational mode is the conversation mode, generating a fourth message in the second language, the fourth message including a conversational response to the first message;

if the first message is in the first language and the operational mode is the translation mode, translating the first message into a fifth message in the second language; and

returning one of the fourth message and the fifth message to the client device if the first message is in the first language.

6. The server device of claim 4, wherein the first message is a speech message in the second language, the third message is a textual message in the first language, the translating the first message into the third message includes:

generating, based on the first message, a fourth message using a speech recognition system for the second language, the fourth message being a textual message in the second language and a speech-to-text transform of the first message; and

translating the fourth message into the third message using machine translation.

7. The server device of claim 4, wherein receiving the first message includes receiving the first message from the client device via a wireless network.

8. A non-transitory computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which, when executed by one or more processors, cause the processors to perform operations comprising:

receiving a first message from a client device;

determining that the first message includes a first portion in a first language and a second portion in a second language, the second language being different than the first language;

translating the first message into a second message in the second language; and

returning the second message to the client device,

wherein the first message is a speech message, the second message is a speech message, the translating further including;

generating, based on the first message, a third message using a bilingual speech recognition system for the first language and the second language, the third message being a textual message including a first portion in the first language and a second portion in the second language, the third message being a speech-to-text transform of the first message;

translating the third message into a fourth message using machine translation, the fourth message being a textual message in the second language; and

generating, based on the fourth message, the second message using speech synthesis, the second message being a text-to-speech transform of the fourth message.

9. The non-transitory computer readable storage medium of claim 8, wherein the one or more programs further comprise instructions for:

receiving an indication of an operational mode from the client device prior to receiving the first message, the operational mode being a conversation mode or a translation mode;

if the operational mode is the translation mode, translating the first message into the second message and returning the second message to the client device; and

if the operational mode is the conversation mode, generating a third message in the second language and returning the third message to the client device, the third message including a conversational response to the first message.

10. The non-transitory computer readable storage medium of claim 8, wherein the first message is a speech message, the determining includes determining the first portion based on an acoustic model associated with the first language and determining the second portion based on an acoustic model associated with the second language.