Method and apparatus for processing voice data

• US 7,590,534 B2
• Filed: 05/09/2002
• Issued: 09/15/2009
• Est. Priority Date: 05/09/2002
• Status: Active Grant

• Current Assignee: Best Buy Health Incorporated (Best Buy Co., Inc.)
• Original Assignee: Healthsense, Inc. (Best Buy Co., Inc.)
• Inventors: Vatland, Danny James
• Primary Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US10/144,436
• Publication Number:
  US 20030212554A1
• Time in Patent Office: 2,686 Days
• Field of Search: 704/235, 704/275, 704/270
• US Class Current: 704/235
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2250/74 with voice recognition means voice activated dialling H04M1/271; voice recognition algorithms G10L15/00
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

One aspect of the present disclosure is a device for processing voice data associated with an application program. The application program has a form therein for entering voice data. The application program provides an identifier associated with voice data for identifying the form the voice data is associated with. The device includes an input portion for receiving voice data and identifier information from the application program. Also included is a translation portion for translating voice data to text data. The translation portion receives the voice data from the input portion and translates the voice data to text data. Also included is an output portion for sending output text data and the identifier information to the application program for association with the form.

Claims

1. A method for processing voice data provided by an application program, the application program for inserting text into a form, the method comprising:

providing a header that is associated with the voice data for identifying a source address and port for an application processing device linked to the application program and identifying a destination address and port for a voice processing device for translating voice data to text data;

receiving voice data associated with the form within the application program;

assigning an identifier to the voice data, wherein the voice data has the identifier associated therewith to identify the form into which the text data is to be placed;

sending the voice data from the application processing device to the voice processing device;

translating the voice data to corresponding text data;

assigning the identifier to the text data, wherein the text data has the identifier associated therewith to identify the form into which the text data is to be placed;

providing a revised header that is associated with the text data for identifying a host address and port for the application processing device and identifying a source address and port for the voice processing device; and

providing the text data and the identifier to the application program for associating the text data with the form.

2. The method of claim 1 wherein the voice data received includes an identifier for identifying the speaker of the voice data and wherein the text data is provided to the application program with the identifier.

3. The method of claim 1 wherein the voice data is sent to the application processing device in real time.

4. The method of claim 1 wherein the voice data is provided by a personal digital assistant (PDA) that is linked using a wireless link to the application processing device, the application processing device providing the voice data and identified in real time via an internet link.

5. The method of claim 1 wherein prior to receiving voice data associated with the form performing the steps of:

displaying a form having a request for information therein, the request for information having a user selectable portion;

selecting the user selectable portion and speaking the requested information wherein the requested information is captured as voice data; and

tagging the voice data with an identifier for associating the voice data with the form.

6. A system for processing voice data comprising:

a processing device running an application program having a form associated therein for inserting text, the processing device configured to receive a voice signal, convert that voice signal into voice data, create an identifier associated with the voice data, assign an identifier to the voice data to associate the voice data to the form of the application program, assign command information for specifying processing of the voice data, and provide an application envelope containing the voice data, identifier and command information;

an application processing device configured for internet connection, the application processing device having a data link for receiving the application envelope in real time from the processing device, the application processing device configured to attach a header to the application envelope, and provide the header and application envelope via an internet connection; and

a voice processing device configured for internet connection and configured to receive the header and application envelope in real time from the application processing device via the internet connection, and acknowledge receipt of the application envelope to permit the application device to disconnect from the internet connection;

wherein the header contains a source address and a source port for the application processing device and a destination address and destination port for the voice processing device,

wherein the voice data is translated to corresponding text data according to the command information,

wherein the identifier is assigned to the text data so the text data has the identifier associated therewith for identifying the form into which the text data is to be placed and the identifier is provided in a text envelope, along with the text data,

wherein a revised header that is associated with the text data for identifying a host address and port for the application processing device and identifying a source address and port for the voice processing device is provided, and

wherein the text envelope and the revised header is provided to the application program for associating the text data with the form.

7. The system for processing voice data of claim 6 wherein the voice processing device is configured for connection to transcription resources for conversion of voice data into text data, wherein the voice processing device is configured to receive text data from the transcription resources.

8. The system for processing voice data of claim 7 wherein the voice processing device is configured to provide the text envelope containing the text data, the identifier associating the text data to the application program, and command information for specifying processing of the text data, wherein the voice processing device is configured to attach a revised header to the text envelope, wherein the voice processing device is configured to send the revised header and text envelope to the application processing device via another internet connection, and wherein the application processing device is configured to pass the text data to the processing device.

9. The system for processing voice data of claim 6 wherein the processing device is a personal data assistant.

10. A computer-readable storage medium storing a computer program product that, when run in a voice-processing platform for processing voice data, the stored program executing the steps of:

receiving a header and envelope information from an internet connected voice data capture device running an application program having a form associated therein for inserting text, the header containing a destination address and a destination port for the voice processing platform, the header further including a source address and a source port for the voice data capture device, the envelope information containing voice data, an identifier for the application program to identify context of the voice data and command information for specifying processing of the voice data by the voice processing platform;

processing the voice data as specified by the command information to convert the voice data into text data, the text data is combined with the identifier to form revised envelope information and a revised header containing a destination address and a destination port for the voice data capture device, the header further including a source address and a source port for the voice processing system platform; and

sending the revised envelope and the revised header to the application program for associating the text data with the form into which the text data is to be placed.

11. The computer-readable storage medium of claim 10 wherein posting the revised envelope is performed after receipt of a request from the Internet connected voice data capture device.