System for accessing data via voice

• US 7,545,917 B2
• Filed: 03/20/2007
• Issued: 06/09/2009
• Est. Priority Date: 01/04/2002
• Status: Expired due to Term

• Current Assignee: Siebel Systems Inc. (Oracle Corporation)
• Original Assignee: Siebel Systems Inc. (Oracle Corporation)
• Inventors: Gorman, Richard, Ambrose, Jesse, Jones, Shannon, Haven, Chris, Harb, Joseph
• Primary Examiner(s): Gauthier; Gerald
• Application Number:
  US11/725,839
• Publication Number:
  US 20070165796A1
• Time in Patent Office: 812 Days
• Field of Search: 379/88.02, 379/88.01, 379/210.01, 455/405, 701/210, 704/273
• US Class Current: 379/88.02
• 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

A system for providing access to data via a voice interface. In one embodiment, the system includes a voice recognition unit and a speech processing server that work together to enable users to interact with the system using voice commands guided by navigation context sensitive voice prompts, and provide user-requested data in a verbalized format back to the users. Digitized voice waveform data are processed to determine the voice commands of the user. The system also uses a “grammar” that enables users to retrieve data using intuitive natural language speech queries. In response to such a query, a corresponding data query is generated by the system to retrieve one or more data sets corresponding to the query. The user is then enabled to browse the data that are returned through voice command navigation, wherein the system “reads” the data back to the user using text-to-speech (TTS) conversion and system prompts.

Claims

1. A voice access system comprising:

a voice recognition unit, wherein

said voice recognition unit comprises

a telephony interface,

a voice recognition client, coupled to said telephony interface,

a client-side module, and

a network interface, coupled to said voice recognition client,

said telephony interface is configured to

enable a user to establish a telephone connection with said voice recognition unit, and

receive user input via said telephone connection,

said network interface is configured to

couple said voice recognition unit to an enterprise data system via a network, and

said client-side module is configured to

enable said voice recognition unit to access said enterprise data system as a client; and

a speech processing server, wherein

said speech processing server comprises

a voice recognition server, and

a network interface,

said network interface is configured to

couple said speech processing server to said voice recognition unit and said enterprise data system via said network,

said voice recognition unit and said speech processing server are configured to interact with one another to

enable said user to request an ad hoc query be performed against data stored by said enterprise data system using a spoken natural language query, and

said user input is said spoken natural language query.

2. The voice access system of claim 1, wherein

said voice recognition unit and said speech processing server are further configured to

interact with one another to

determine query criteria,

send said query criteria to said enterprise data system,

receive data from said enterprise data system, and

provide feedback data to said user via said telephone connection;

said query criteria correspond to said ad hoc query;

said data is based on said query criteria; and

said feedback data corresponds to data received from said enterprise data system in a verbal format.

3. The voice access system of claim 2, wherein said voice recognition unit and said speech processing server are further configured to interact with one another to:

authenticate said user using a login process, wherein said user is identified using a unique identifier;

determine enterprise data system log-in data, wherein said enterprise data system log-in data is configured to enable said user to access said enterprise data system; and

automatically log said user into said enterprise data system using said enterprise data system log-in data.

4. The voice access system of claim 3, further comprising:

a local database, wherein

said voice recognition unit is coupled to said local database,

said local database is configured to store a plurality of unique identifiers and corresponding pass-codes, and

said voice access system is configured to authenticate said user by virtue of being configured to

receive user-identification information from said user via said telephone connection,

compare said user-identification information with user-identification data stored in said local database, and

authenticate said user, if said user-identification information received from said user matches said user-identification data stored in said local database.

5. The voice access system of claim 2, wherein said voice recognition client is configured to convert voice waveform data into text data.

6. The voice access system of claim 5, wherein

said voice recognition client comprises a voice recognition server;

and

said voice recognition client is configured to

submit voice waveform data to said voice recognition server,

convert said voice waveform data into text data using said voice recognition server, and

make said text data available to said voice recognition client.

7. The voice access system of claim 2, wherein

said voice recognition unit comprises a voice application;

and

said voice application is configured to manage interactions with said voice access system.

8. The voice access system of claim 2, wherein said speech processing server further comprises:

a text-to-speech server, wherein

said text-to-speech server is configured to convert text data into computer-generated audible speech, and

said computer-generated audible speech corresponds to said data.

9. The voice access system of claim 2, wherein said voice recognition unit and said speech processing server are further configured to interact with one another to:

convert said spoken natural language query into a data request in a text form; and

identify an object and data criteria corresponding to said spoken natural language query,

wherein said being configured to identify is based on said data request.

10. The voice access system of claim 9, wherein

said enterprise data system comprises

an object manager, and

a data manager;

said voice recognition unit and said speech processing server are further configured to

interact with one another to

communicate information corresponding to said object and said data criteria to said object manager; and

said enterprise data system is configured to

formulate a data query based on said object and said data criteria, wherein

said being configured to formulate uses enterprise database schema information available to said data manager, and

return data retrieved by said data query to said voice recognition unit.

11. The voice access system of claim 2, wherein said voice recognition unit and said speech processing server are further configured to interact with one another to:

authenticate said user with said voice access system using a login process, wherein said user is identified by a unique identifier;

retrieve data pertaining to a selected object from said enterprise database, wherein said data is retrieved using said unique identifier; and

provide feedback data corresponding to any data that are retrieved in a verbal format to said user via said telephone connection.