Method and systems for accessing data from a network via telephone, using printed publication

• US 7,864,929 B2
• Filed: 02/10/2005
• Issued: 01/04/2011
• Est. Priority Date: 02/13/2004
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Carro, Fernando Incertis
• Primary Examiner(s): SING, SIMON P
• Application Number:
  US11/055,768
• Publication Number:
  US 20050180401A1
• Time in Patent Office: 2,154 Days
• Field of Search: 370/352, 379 8801- 8804, 379/88.13, 379/88.14, 704/246
• US Class Current: 379/88.04
• CPC Class Codes: H04M 2201/39 using speech synthesis speech synthesis per se G10L13/00
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

A method and systems to access information related to items printed on publications by voice commands generated by a user through a telephone. To access additional information, the user dials on a telephone the Interactive Voice Response (IVR) service identifier and the publication identifier. A publication link table is associated to the publication identifier and provides a list of the item names on the selected publication. The IVR recognizes the name of the item pronounced by the user and determines the address associated to this name. The proxy server accesses the information located at this address and forwards it to the IVR wherein it is converted by a text-to-speech for the user'"'"'s telephone.

Claims

1. A computer-implemented method for providing electronically stored information to a user via a telephone, the electronically stored information being associated with a printed publication, the printed publication having printed thereon an alphanumeric identifier and a plurality of information items associated with the alphanumeric identifier, the method comprising acts of:

receiving and electronically recording, by an information server, the alphanumeric identifier and the plurality of information items associated with the alphanumeric identifier;

receiving, by a voice server comprising a speech recognition unit and a text to speech unit, a first utterance pronounced by the user and transmitted via the telephone, the first utterance comprising the alphanumeric identifier from the printed publication;

recognizing, by the speech recognition unit of the voice server, the alphanumeric identifier from the first utterance received by the voice server;

receiving, by the voice server from the information server, the plurality of information items associated with the alphanumeric identifier recognized by the speech recognition unit of the voice server;

receiving, by the voice server, a second utterance pronounced by the user and transmitted via the telephone, the second utterance identifying at least one information item of the plurality of information items from the printed publication;

recognizing, by the speech recognition unit of the voice server, information identifying the at least one information item from the second utterance received by the voice server, using a reduced grammar based at least in part on the plurality of information items received by the voice server from the information server;

accessing, by the information server, the electronically stored information over at least one communication network, using a network address associated with the at least one information item recognized by the speech recognition unit of the voice server;

rendering, by the text to speech unit of the voice server, the electronically stored information accessed by the information server as a first audio signal; and

transmitting, by the voice server, the first audio signal to the user via the telephone.

2. The method of claim 1, wherein:

the electronically stored information comprises explanatory information regarding the at least one information item and an index for additional explanatory information regarding the at least one information item; and

the act of rendering, by the text to speech unit of the voice server, the electronically stored information comprises an act of rendering the index for additional explanatory information in a different type of voice than the explanatory information to alert the user that the index for additional explanatory information is a selectable index that enables the user to obtain the additional explanatory information.

3. The method of claim 2, further comprising acts of:

receiving, by the voice server, a third utterance pronounced by the user and transmitted via the telephone, the third utterance comprising a predetermined word in the index for additional explanatory information;

recognizing, by the speech recognition unit of the voice server, the predetermined word from the third utterance received by the voice server;

accessing, by the information server, the additional explanatory information over the at least one communication network, in response to recognizing the predetermined word in the index for additional explanatory information;

rendering, by the text to speech unit of the voice server, the additional explanatory information accessed by the information server as a second audio signal; and

transmitting, by the voice server, the second audio signal to the user via the telephone.

4. The method of claim 3, wherein the electronically stored information is a web page and the index for additional explanatory information is a hyperlink on the web page.

5. The method of claim 1 further comprising acts of:

distributing the printed publication to the user; and

instructing the user to pronounce the first utterance comprising the alphanumeric identifier.

6. The method of claim 2 further comprising acts of:

distributing the printed publication to the user; and

instructing the user to pronounce the first utterance comprising the alphanumeric identifier.

7. The method of claim 1, wherein the voice server and the information server are formed by a single server.

8. The method of claim 1, wherein the alphanumeric identifier is not rendered as an option to the user by the voice server.

9. A system for providing electronically stored information to a user via a telephone, the electronically stored information being associated with a printed publication, the printed publication having printed thereon an alphanumeric identifier and a plurality of information items associated with the alphanumeric identifier, the system comprising:

a voice server comprising a speech recognition unit and a text to speech unit, the voice server adapted to receive a first utterance pronounced by the user and transmitted via the telephone, the first utterance comprising the alphanumeric identifier from the printed publication, wherein the speech recognition unit of the voice server is adapted to recognize the alphanumeric identifier from the first utterance received by the voice server; and

an information server adapted to transmit to the voice server the plurality of information items associated with the alphanumeric identifier recognized by the speech recognition unit of the voice server, wherein;

the information server is further adapted to receive and electronically record the alphanumeric identifier and the plurality of information items associated with the alphanumeric identifier;

the voice server is further adapted to receive a second utterance pronounced by the user and transmitted via the telephone, the second utterance identifying at least one information item of the plurality of information items from the printed publication;

the speech recognition unit of the voice server is further adapted to recognize information identifying the at least one information item from the second utterance received by the voice server, using a reduced grammar based at least in part on the plurality of information items retrieved by the information server;

the information server is further adapted to access the electronically stored information over at least one communication network, using a network address associated with the at least one information item recognized by the speech recognition unit of the voice server;

the text to speech unit of the voice server is adapted to render the electronically stored information accessed by the information server as a first audio signal; and

the voice server is further adapted to transmit the first audio signal to the user via the telephone.

10. The system of claim 9, wherein:

the electronically stored information comprises explanatory information regarding the at least one information item and an index for additional explanatory information regarding the at least one information item; and

the text to speech unit of the voice server is further adapted to render the index for additional explanatory information in a different type of voice than the explanatory information to alert the user that the index for additional explanatory information is a selectable index that enables the user to obtain the additional explanatory information.

11. The system of claim 10, wherein:

the voice server is further adapted to receive a third utterance pronounced by the user and transmitted via the telephone, the third utterance comprising a predetermined word in the index for additional explanatory information;

the speech recognition unit of the voice server is further adapted to recognize the predetermined word from the third utterance received by the voice server;

the information server is further adapted to access the additional explanatory information over the at least one communication network, in response to recognizing the predetermined word in the index for additional explanatory information;

the text to speech unit of the voice server is further adapted to render the additional explanatory information accessed by the information server as a second audio signal; and

the voice server is further adapted to transmit the second audio signal to the user via the telephone.

12. The system of claim 11, wherein the electronically stored information is a web page and the index for additional explanatory information is a hyperlink on the web page.

13. The system of claim 9, wherein the voice server and the information server are formed by a single server.

14. The system of claim 9, wherein the voice server does not render the alphanumeric identifier as an option to the user.

15. A system for providing electronically stored information to a user via a telephone, the electronically stored information being associated with a printed publication, the printed publication having printed thereon an alphanumeric identifier and a plurality of information items associated with the alphanumeric identifier, the system comprising:

a voice server comprising a speech recognition unit, a dual tone multi-frequency (“

DTMF”

) unit and a text to speech unit, wherein the DTMF unit is adapted to receive a first DTMF entry transmitted from the user via the telephone, the first DTMF entry comprising the alphanumeric identifier from the printed publication, and wherein the speech recognition unit of the voice server is adapted to recognize the alphanumeric identifier from the first DTMF entry received by the DTMF unit of the voice server; and

an information server adapted to communicate with the voice server and to retrieve the plurality of information items associated with the alphanumeric identifier recognized by the speech recognition unit of the voice server, wherein;

the DTMF unit of the voice server is further adapted to receive a second DTMF entry transmitted from the user via the telephone, the second DTMF entry identifying at least one information item of the plurality of information items from the printed publication;

the speech recognition unit of the voice server is further adapted to recognize information identifying the at least one information item from the second DTMF entry received by the DTMF unit of the voice server, using a reduced grammar based at least in part on the plurality of information items retrieved by the information server;

the information server is further adapted to access the electronically stored information over at least one communication network, using a network address associated with the at least one information item recognized by the speech recognition unit of the voice server;

the text to speech unit of the voice server is adapted to render the electronically stored information accessed by the information server as a first audio signal; and

the DTMF unit of the voice server is further adapted to transmit the first audio signal to the user via the telephone.

16. The system of claim 15, wherein:

the electronically stored information comprises explanatory information regarding the at least one information item and an index for additional explanatory information regarding the at least one information item; and

the text to speech unit of the voice server is further adapted to render the index for additional explanatory information in a different type of voice than the explanatory information to alert the user that the index for additional explanatory information is a selectable index that enables the user to obtain the additional explanatory information.

17. The system of claim 15, wherein:

the DTMF unit of the voice server is further adapted to receive a third DTMF entry transmitted from the user via the telephone, the third DTMF entry comprising a predetermined word in the index for additional explanatory information;

the speech recognition unit of the voice server is further adapted to recognize the predetermined word from the third DTMF entry received by the DTMF unit of the voice server;

the information server is further adapted to access the additional explanatory information over the at least one communication network, in response to recognizing the predetermined word in the index for additional explanatory information;

the text to speech unit of the voice server is further adapted to render the additional explanatory information accessed by the information server as a second audio signal; and

the DTMF unit of the voice server is further adapted to transmit the second audio signal to the user via the telephone.

18. The system of claim 15, wherein the voice server does not render the alphanumeric identifier as an option to the user.