Device and method for the speech input of a destination into a destination guiding system by means of a defined input dialogue

• US 20030014255A1
• Filed: 07/16/2002
• Published: 01/16/2003
• Est. Priority Date: 03/15/2000
• Status: Active Grant

• Current Assignee: BMW AG (Bayerische Motoren Werke AG)
• Original Assignee: BMW AG (Bayerische Motoren Werke AG)
• Inventors: Said, Tarek, Steingrubner, Mihai
• Granted Patent: US 7,209,884 B2
• Time in Patent Office: Days
• US Class Current: 704/270
• CPC Class Codes: G01C 21/3608 using speech input, e.g. using speech recognition
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

In the case of a system for the voice input of a destination by means of a defined input dialog into a destination guiding system in the real-time operation, having devices by which an entered voice statement of a user is detected by means of a voice recognition device, is compared with stored voice statements and is classified according to its recognition probability and by means of which the stored voice statement is recognized as the entered voice statement with the highest recognition probability, the stored voice statements assigned to a destination are composed at least of the destination name and at least a regionally limiting additional information unambiguously identifying the destination name, each destination name being filed with a flag symbol in a first database and each additional information being filed in a second database.

Claims

1. System for the voice input of a destination by means of a defined input dialog into a destination guiding system in the real-time operation, having devices by which an entered voice statement of a user is detected by means of a voice recognition device, is compared with stored voice statements and is classified according to its recognition probability and by means of which the stored voice statement is recognized as the entered voice statement with the highest recognition probability, characterized in that the stored voice statements assigned to a destination are composed at least of the destination name and at least a regionally limiting additional information unambiguously identifying the destination name, each destination name being filed with a flag symbol in a first database (1) and each additional information being filed in a second database (2).

2. System according to claim 1,

characterized in that prepositions are filed in a third database (3) which are used for separating the destination name and the additional information in an entered voice statement.

3. Process having a system according to claim 1 or 2,

characterized in that, after the input of a voice statement, it is checked by the voice recognition device whether at least a part of the voice statement is an additional information and the user is guided, if required, in the further course, to the voice input of an additional information or to a defined phrase input by which the voice recognition device can recognize that at least a part of the voice statement is an additional information.

4. Process according to claim 3 or process having a system according to claim 1 or 2,

characterized in that, after the input of a voice statement, the latter is assigned by the voice recognition device to one of at least two input categories, a first input category being defined as a phrase input if the voice recognition device considers a part of the voice statement to be an additional information, and a second input category being defined as a single-word input if the voice recognition device considers no part of the voice statement to be an additional information.

5. Process according to claim 3 or 4,

characterized in that, when a part of the voice statement is recognized as additional information in the second database (2), a partial data stock assigned to this additional information is generated from the first database (1), in which partial data stock the desired destination name is searched on the basis of the entered voice statement.

6. Process according to claim 4,

characterized in that, when no part of the voice statement is considered to be entered additional information, the entire voice statement is searched in the second database (2), and in that the stored additional information with the highest recognition probability is selected from the second database (2) as the entered destination name.

7. Process according to claim 6,

characterized in that, if an additional information is not recognized in the second database (2), the user is requested within the scope of the further input dialog to carry out a voice input of an additional information.

8. Process according to one of claims 3 to 7,

characterized in that the defined phrase input consists at least of a destination name and an additional information.

9. Process according to one of claims 3 to 8,

characterized in that an entered voice statement is categorized as a phrase input when a part of the voice statement is recognized as a preposition or as additional information which is preceded by a part of the voice statement.