Method of switching between dialog systems

• US 20030061052A1
• Filed: 09/23/2002
• Published: 03/27/2003
• Est. Priority Date: 09/26/2001
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Breuer, Richard
• Granted Patent: US 7,343,290 B2
• Time in Patent Office: Days
• US Class Current: 704/266
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 2203/2061 Language aspects
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals

Abstract

The invention concerns a method of switching from one original dialog system (1), which communicates with the user using a speech recognition and/or speech output unit (6), to a target dialog system (2), which also communicates with the user using a speech recognition and/or speech output unit (7), whereby the language of the speech recognition and/or speech output unit (7) of the target dialog system (2) can be set. The original dialog system (1) transfers a language information parameter (P₂) to the target dialog system (2), as a result of which the language which the original dialog system (1) used for communication with the user is specified. The target dialog system (2) uses this language information parameter (P₂) to set the language of the speech recognition and/or speech output unit (7) for further communication with the user.

Claims

1. A method of switching a user from one original dialog system (1), which communicates with the user using a speech recognition and/or speech output unit (6) to a target dialog system (2) which communicates with the user using a speech recognition and/or speech output unit (7) which can be set as desired to one of several languages, characterized in that, during switching, a language information parameter (P₂) is sent to the target dialog system (2), which language information parameter represents a language in which the communication between the user and the original dialog system (1) has taken place, and, using this language information parameter, the speech recognition and/or speech output unit (7) of the target dialog system (2) is automatically set to a suitable language for communication with the user.

2. A method as claimed in claim 1, characterized in that, together with the language information parameter (P₂), at least one further parameter (P₁, P₃), characterizing the user and/or a connection between the user and the original dialog system (1), is transmitted to the target dialog system.

3. A method as claimed in claim 1 or 2, characterized in that, during the transmission of the language information parameter (P₂), a code (S₂) is sent to the target dialog system (2), indicating that a language information parameter (P₂) is being sent and/or the form in which the language information parameter (P₂) is coded.

4. A method as claimed in claims 1 to 3, characterized in that the language information parameter is sent to the target dialog system within a communication protocol used for building the connection between the original dialog system and the target dialog system.

5. A method as claimed in claim 4, characterized in that the communication protocol is a telephony connection protocol.

6. A method as claimed in one of claims 1 to 3, characterized in that the language information parameter is sent to the target dialog system within a communication protocol used for data transfer during an existing connection between the original dialog system and the target dialog system.

7. A method as claimed in claim 4 or 6, characterized in that the communication protocol is an Internet protocol or a protocol based on an Internet protocol.

8. A method as claimed in one of claims 1 to 3, characterized in that the language information parameter (P₂) is stored in a temporary store (4) of a communication network by the original dialog system (1) and is transmitted from there to the target dialog system (2).

9. A method as claimed in one of claims 1 to 8, characterized in that the language information parameter (P₂) is transmitted in the form of an internationally standardized code.

10. A dialog system (1) for implementation according to one of claims 1 to 9, which communicates with the user using a speech recognition and/or speech output unit, with a means of switching the user to a target dialog system (2), characterized by a means for transmitting a language information parameter (P₂) to the target dialog system (2) during the switching, whereby the language information parameter (P₂) represents a language in which the communication between the user and the dialog system (1) has taken place.

11. A dialog system (2) for implementation of a method according to one of claims 1 to 9, which communicates with the user using a speech recognition and/or speech output unit (7) which can be set as desired to one out of several languages, characterized by a means for receiving a language information parameter (P₂) during the switching of a user from one original dialog system (1) to the dialog system (2), whereby the language information parameter (P₂) represents a language in which the communication between the user and the original dialog system (1) has taken place, and a means (8) for automatically setting the speech recognition and/or speech output unit (7) of the dialog system (2) to a suitable language for communication with the user in question using the language information parameter (P₂).