Speaker-dependent voice recognition method and voice recognition system

• US 20070100632A1
• Filed: 03/03/2004
• Published: 05/03/2007
• Est. Priority Date: 03/25/2003
• Status: Active Grant

• Current Assignee: Siemens AG
• Original Assignee: Siemens AG
• Inventors: Aubauer, Roland
• Granted Patent: US 7,835,913 B2
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/0631 Creating reference templates; Clustering

Abstract

A speaker-dependent voice recognition method is provided involving the use of a voice recognition system, during which voice utterances of the user are trained, and commands are assigned to the trained voice utterances. The present disclosure seeks to carry out a training of new commands in a time-saving manner. To this end, in the event of a non-recognition of a voice utterance, the voice recognition system provides the user with the opportunity to immediately assign the voice utterance to a new command.

Claims

1-9. -9. (canceled)

10. A speaker-dependent voice recognition method with a voice recognition system, the method comprising:

providing that voice utterances of a user are trained and commands are assigned to the trained voice utterances; and

providing the user, upon non-recognition of a voice utterance and via the voice recognition system, an opportunity to immediately assign the voice utterance to a new command.

11. A speaker-dependent voice recognition method as claimed in claim 10, wherein, upon the non-recognition of the voice utterance by the voice recognition system, the user may one of repeat the voice utterance and assign a new command to the voice utterance.

12. A speaker-dependent voice recognition method as claimed in claim 10, wherein if no command has yet been assigned to a voice utterance, the voice recognition system, after having been activated, offers the training of a new command.

13. A speaker-dependent voice recognition method as claimed in claim 10, wherein upon the non-recognition of a voice utterance for a command already trained by the voice recognition system, the user may select the command and assign the voice utterance to the selected command.

14. A speaker-dependent voice recognition method as claimed in claim 10, wherein for recognition of a voice utterance, a voice pattern is generated which is assigned to the voice utterance.

15. A speaker-dependent voice recognition method as claimed in claim 10, wherein before a command is assigned to a voice utterance, a check is carried out to determine whether the voice utterance is similar to previously stored voice utterances.

16. A voice recognition system for a speaker-dependent recognition of voice, comprising:

a voice recording device for recording a voice utterance of a user of the voice recognition system;

a search engine for accessing a database which contains an assignment between voice utterances and commands in order to find a command assigned to the voice utterance; and

a conversion device for converting the command found due to the voice utterance, wherein upon non-recognition of the voice utterance, the voice recognition system provides the user with an opportunity to immediately assign the voice utterance to a new command.

17. A voice recognition system as claimed in claim 16, wherein the voice recording device is connected to a memory in which the voice utterance is temporarily stored and which is connected to the database for reading the voice utterance into the database.

18. A voice recognition system as claimed in claim 16, further comprising a feature extraction device for generating a voice pattern from the voice utterance, the feature extraction device being arranged between the voice recording device and the memory, with the voice pattern replacing the voice utterance.