Motor vehicle with a speech interface

• US 7,873,517 B2
• Filed: 11/09/2006
• Issued: 01/18/2011
• Est. Priority Date: 11/09/2006
• Status: Active Grant

• Current Assignee: Volkswagen of America Inc (Volkswagen AG)
• Original Assignee: Volkswagen of America Inc (Volkswagen AG)
• Inventors: Williams, Carly, Bergmann, Carsten, Prieto, Ramon, Imam, M. Kashif, Cheung, Wai Yin
• Primary Examiner(s): Sked; Matthew J
• Application Number:
  US11/595,113
• Publication Number:
  US 20080114598A1
• Time in Patent Office: 1,531 Days
• Field of Search: None
• US Class Current: 704/255
• CPC Class Codes: G10L 15/005 Language recognition
• CPC Class Codes: G10L 15/10 using distance or distortion measures between unknown speech and reference templates

Abstract

A motor vehicle has a speech interface for an acoustic input of commands for operating the motor vehicle or a module of the motor vehicle. The speech interface includes a speech recognition database in which a substantial portion of commands or command components, which can be input, are stored in a version according to a pronunciation in a first language and in a version according to a pronunciation in at least a second language, and a speech recognition engine for automatically comparing an acoustic command to commands and/or command components, which are stored in the speech recognition database, in a version according to the pronunciation in the first language and to commands and/or command components, which are stored in the speech recognition database, in a version according to the pronunciation in the second language.

Claims

1. A motor vehicle comprising:

a speech interface configured to receive an acoustic input of commands for operating one of a motor vehicle and a module of the motor vehicle;

said speech interface including a speech recognition database and a speech recognition engine;

said speech recognition database storing a substantial portion of at least one of commands and command components which can be input, in a version according to a pronunciation in a first language and in a version according to a pronunciation in at least a second language, such that each given one of the substantial portion of the at least one of commands and command components is stored in a version according to a pronunciation in the first language and in a version according to a pronunciation in at least the second language;

said speech recognition engine being configured to automatically compare an acoustic command to at least one of commands and command components, which are stored in said speech recognition database, in a version according to the pronunciation in the first language and to at least one of commands and command components, which are stored in said speech recognition database, in a version according to the pronunciation in the second language;

said speech interface including a speech recognition acoustic model trained in the first language and in the second language; and

said speech interface including a multilingual grammar module, said multilingual grammar module including grammar and phrases in the first language and in the second language.

2. The motor vehicle according to claim 1, wherein said speech interface includes a grapheme-to-phoneme module assigned to the first language, said grapheme-to-phoneme module is configured to generate a new entry in said speech recognition database for at least one of a new word and a new name.

3. The motor vehicle according to claim 2, wherein:

said grapheme-to-phoneme module assigned to the first language is a first grapheme-to-phoneme module; and

said speech interface further includes a second grapheme-to-phoneme module assigned to the second language, said second grapheme-to-phoneme module is configured to generate a new entry in said speech recognition database for at least one of the new word and the new name.

4. The motor vehicle according to claim 1, wherein said speech interface includes a speech output interface configured to provide an acoustic output of information.

5. The motor vehicle according to claim 4, wherein said speech output interface includes a language selection module configured to automatically select one of the first language and the second language for an output of information.

6. The motor vehicle according to claim 5, wherein said language selection module includes a counter configured to count at least one of words and components of a command having been input, distinguished according to a use of the first language and the second language for individual words and components.

7. The motor vehicle according to claim 6, wherein said language selection module includes a language switch configured to automatically select one of the first language and the second language for the output of the information in dependence of a number of at least one of words and components of the command having been input in the first language and the second language within a counting interval.

8. The motor vehicle according to claim 5, wherein said language selection module includes a counter configured to count at least one of words and components of a command having been input, distinguished according to a use of the first language and the second language for individual words and components within a counting interval.

9. The motor vehicle according to claim 4, wherein said speech output interface includes a text-to-speech module trained with the first language and the second language for transforming a text command into a speech output.

10. The motor vehicle according to claim 4, wherein said speech output interface includes a speech output database storing a substantial portion of information which can be output, in a version according to a pronunciation in the first language and in a version according to a pronunciation in the second language.

11. A motor vehicle comprising:

a speech interface including a speech input interface configured to receive an acoustic input of commands for operating one of a motor vehicle and a module of the motor vehicle;

said speech input interface including a speech identification module with a speech recognition database storing a substantial portion of at least one of commands and command components which can be input, in a version according to a pronunciation in a first language and in a version according to a pronunciation in at least a second language, such that each given one of the substantial portion of the at least one of commands and command components is stored in a version according to a pronunciation in the first language and in a version according to a pronunciation in at least the second language;

said speech identification module being configured to assign a pronunciation of at least one of a command and a command component to one of the first language and the at least second language;

said speech interface including a speech recognition acoustic model trained in the first language and in the second language; and

said speech interface including a multilingual grammar module, said multilingual grammar module including grammar and phrases in the first language and in the second language.

12. The motor vehicle according to claim 11, including a speech output interface operatively connected to said speech input interface and configured to provide an acoustic output of information.

13. The motor vehicle according to claim 12, wherein said speech output interface includes a language selection module configured to automatically select the language as a language to be used for the acoustic output of information.

14. A motor vehicle comprising:

a speech interface configured to provide an acoustic output of information;

said speech input interface including a speech identification module with a speech recognition database storing a substantial portion of at least one of commands and command components which can be input, in a version according to a pronunciation in a first language and in a version according to a pronunciation in at least a second language, such that each given one of the substantial portion of the at least one of commands and command components is stored in a version according to a pronunciation in the first language and in a version according to a pronunciation in at least the second language;

said speech interface including a language selection module configured to automatically select one of the first language and the at least second language for the output of information;

said speech interface including a speech recognition acoustic model trained in the first language and in the second language; and

said speech interface including a multilingual grammar module, said multilingual grammar module including grammar and phrases in the first language and in the second language.

15. The motor vehicle according to claim 14, wherein said language selection module includes a counter configured to count at least one of words and components of a command having been input, distinguished according to a language used for at least one of individual words and components.

16. The motor vehicle according to claim 15, wherein said language selection module includes a language switch configured to automatically select a language for the output of information in dependence of a respective number of at least one of words and components of a command having been input in a respective language within a counting interval.

17. The motor vehicle according to claim 14, wherein said language selection module includes a counter configured to count at least one of words and command components having been input, distinguished according to a language used for at least one of individual words and components within a counting interval.

18. The motor vehicle according to claim 14, wherein said speech interface includes a multilingual text-to-speech module configured to transform a text command into a speech output.

19. The motor vehicle according to claim 14, wherein said speech interface includes a multilingual speech output database.