System and method for intelligent language switching in automated text-to-speech systems

• US 9,640,173 B2
• Filed: 09/10/2013
• Issued: 05/02/2017
• Est. Priority Date: 09/10/2013
• Status: Active Grant

• Current Assignee: Hyundai Motor Company (Hyundai Motor Group), Kia Corp.
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Pulz, Gregory, Blanchard, Harry E., Zhang, Lan
• Primary Examiner(s): SPOONER, LAMONT M
• Application Number:
  US14/022,991
• Publication Number:
  US 20150073770A1
• Time in Patent Office: 1,330 Days
• Field of Search: 704 2- 8
• 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 13/047 Architecture of speech synthesisers
• CPC Class Codes: G10L 13/086 Detection of language

Abstract

Systems, methods, and computer-readable storage media for providing for intelligent switching of languages and/or pronunciations in a text-to-speech system. As the system receives text, the text is analyzed to identify portions which should have speech constructed using a pronunciation distinct from the remaining portions of the text. The text-to-speech system uses multiple pronunciation dictionaries to generate and produce speech corresponding to the text, where the identified portions of the text are in a different language or have a different accent from the remainder of the text. Having generated speech corresponding to the text in multiple languages, accents, or dialects, the system combines the portions, then communicates the speech to the text recipient.

Claims

1. A method comprising:

receiving text having a first part of the text and a second part of the text, wherein the text is associated with one language;

identifying a recipient of speech to be generated from the text;

identifying a location of the recipient of the speech;

when the location comprises a first location;

selecting, via a processor, a first language for the first part of the text and a second language for the second part of the text;

generating, via the processor, first speech from the text, wherein the first speech comprises a first portion corresponding to the first part of the text and a second portion corresponding to the second part of the text, the first portion in the first language and the second portion in the second language; and

communicating the first speech to the recipient; and

when the location comprises a second location that differs from the first location;

generating second speech from the text wherein the second speech comprises the first portion and the second portion both being in a same language; and

communicating the second speech to the recipient.

2. The method of claim 1, wherein the first language is a primary language of the recipient, and the second language is selected based on an original pronunciation of the second part of the text.

3. The method of claim 2, wherein the first part of the text is an address number and the second part of the text is a street name.

4. The method of claim 1, wherein the first language and the second language correspond to distinct regional accents of a single language.

5. The method of claim 1, wherein the first language and the second language is further selected based on one of an age, an ethnicity, and a language of a sender of the text.

6. The method of claim 1, further comprising:

receiving, from the recipient, input indicating a category corresponding to one of the first part of the text and the second part of the text.

7. The method of claim 1, wherein the generating of the speech occurs on a mobile device.

8. The method of claim 1, further comprising identifying the first portion and the second portion using a first language pronunciation database corresponding to the first language and a second language pronunciation database corresponding to the second language.

9. A system comprising:

a processor; and

a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising;

receiving text having a first part of the text and a second part of the text, wherein the text is associated with one language;

identifying a recipient of speech to be generated from the text;

identifying a location of the recipient of the speech;

when the location comprises a first location;

selecting a first language for the first part of the text and a second language for the second part of the text;

generating first speech from the text, wherein the first speech comprises a first portion corresponding to the first part of the text and a second portion corresponding to the second part of the text, the first portion in the first language and the second portion in the second language; and

communicating the first speech to the recipient; and

when the location comprises a second location that differs from the first location;

generating second speech from the text wherein the second speech comprises the first portion and the second portion both being in a same language; and

communicating the second speech to the recipient.

10. The system of claim 9, wherein the first language is a primary language of the recipient, and the second language is selected based on an original pronunciation of the second part of the text.

11. The system of claim 10, wherein the first part of the text is an address number and the second part of the text is a street name.

12. The system of claim 9, wherein the first language and the second language correspond to distinct regional accents of a single language.

13. The system of claim 9, wherein the first language and the second language is further selected based on one of an age, an ethnicity, and a language of a sender of the text.

14. The system of claim 9, the computer-readable storage medium having additional instructions stored which result in the operations further comprising:

receiving, from the recipient, input indicating a category corresponding to one of the first part of the text and the second part of the text.

15. The system of claim 9, wherein the generating of the speech occurs on a mobile device.

16. A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:

receiving text having a first part of the text and a second part of the text, wherein the text is associated with one language;

identifying a recipient of speech to be generated from the text;

identifying a location of the recipient of the speech;

when the location comprises a first location;

selecting a first language for the first part of the text and a second language for the second part of the text;

generating first speech from the text, wherein the first speech comprises a first portion corresponding to the first part of the text and a second portion corresponding to the second part of the text, the first portion in the first language and the second portion in the second language; and

communicating the first speech to the recipient; and

when the location comprises a second location that differs from the first location;

generating second speech from the text wherein the second speech comprises the first portion and the second portion both being in a same language; and

communicating the second speech to the recipient.

17. The computer-readable storage device of claim 16, wherein the first language is a primary language of the recipient, and the second language is selected based on an original pronunciation of the second part of the text.

18. The computer-readable storage device of claim 17, wherein the first part of the text is an address number and the second part is a street name.