Method and apparatus for improving the utility of speech recognition

• US 6,584,179 B1
• Filed: 10/24/1997
• Issued: 06/24/2003
• Est. Priority Date: 10/21/1997
• Status: Expired due to Term

• Current Assignee: Bell Canada (BCE Incorporated)
• Original Assignee: Bell Canada (BCE Incorporated)
• Inventors: Bouchard, Jean, Fortier, Stéphane, Reid, Colin A., Williams, L. Lloyd
• Primary Examiner(s): WEAVER, SCOTT LOUIS
• Application Number:
  US08/957,735
• Time in Patent Office: 2,069 Days
• Field of Search: 379/88.01, 379/88.03, 379/88.04, 379/88.22, 379/201, 379/207, 379/210, 379/211, 379/212, 379/213, 379/214, 379/93.17, 379/93.23, 379/201.04, 379/213.01, 379/218.01, 379/428.03, 704/231, 704/251, 704/252, 704/257, 704/270, 704/275
• US Class Current: 379/88.01
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: H04M 1/271 controlled by voice recognition
• CPC Class Codes: H04M 2201/38 Displays
• 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 3/42323 PBX's with CTI arrangements
• CPC Class Codes: H04M 3/4931 Directory assistance systems

Abstract

A method and apparatus for improving the utility of speech recognition is described. The method involves capturing a spoken word, passing the spoken word to a speech recognition algorithm, receiving at least one text representation of the spoken word from the speech recognition algorithm, and passing a text representation of the spoken word to a display telephone to permit the user to select the correct representation of the voice response. The apparatus is an access server which communicates with a display telephone, a speech recognition algorithm which responds to queries from the access server and one or more databases which likewise respond to queries from the access server. The method and apparatus are particularly useful in automating such functions as telephone directory services using display telephones. The advantage is the ability to completely automate directory services for owners of display telephones and to significantly broaden the applications for speech recognition as a tool in information retrieval and transaction processing.

Claims

1. A method of improving the utility of speech recognition of words spoken by a speaker, comprising:

a) capturing in electronic form using a telephone voice terminal connected to a telephone network a word spoken by the speaker, the word being captured at an access server which is accessed by the speaker using a connection over a voice grade telephone line;

b) passing the word to a speech recognition algorithm in the telephone network;

c) receiving from the speech recognition algorithm at least one representation of the word;

d) displaying for the speaker as text the at least one representation of the word to permit the speaker to select a correct representation of the word from among the at least one representation; and

e) repeating the steps of a)-d) in an event that none of the representation of the word are verified as correct, or enabling the speaker to communicate the at least one word to the access server in another way.

2. A method of improving the utility of speech recognition of words spoken by a speaker as claimed in claim 1 wherein the telephone is a display telephone which conforms to an Analog Display Services Interface (ADSI) standard.

3. A method of improving the utility of speech recognition of words spoken by a speaker as claimed in claim 1 wherein the speech recognition algorithm resides on another server connected to the access server by a communications network.

4. A method of improving the utility of speech recognition of words spoken by a speaker as claimed in claim 1 wherein the other way of communicating the word comprises verbally spelling the word and the speech recognition algorithm to which the word is passed is an alpha speech recognition algorithm.

5. A method of improving the utility of speech recognition of words spoken by a speaker as claimed in claim 1 wherein the speaker communicates the word in another way by manually spelling the word using a dial pad of a display telephone.

6. A method of improving the utility of speech recognition of words spoken by a speaker as claimed in claim 5 wherein keys on the dial pad are pressed once for each relative position of a letter on the key in order to manually spell the spoken name so that if the letter appears in a first position on the key, the key is pressed once to produce the letter, if the letter is in a second position on the key, the key is pressed twice to produce the letter and if the letter is in a third position on the key, the key is pressed three times to produce the letter.

7. A method of automating telephone directory services for a telephone user having a display telephone, comprising the steps of:

a) prompting the user for names used as indicia to locate an entity in the directory;

b) accepting from the user a spoken name for each index;

c) passing each spoken name to a speech recognition algorithm and accepting from the speech recognition algorithm at least one representation of the spoken name;

d) displaying as text on the display telephone the at least one representation of the spoken name to permit the user to select a correct representation of the spoken name; and

e) assembling a query to the directory after a correct representation of each index has been selected in order to retrieve a record for the entity from the directory.

8. A method of automating telephone directory services for a telephone user having a display telephone as claimed in claim 7 further comprising the step of providing the user with another way of entering an index in an event that the desired index cannot be recognized by the speech recognition algorithm.

9. A method of automating telephone directory services for a telephone user having a display telephone as claimed in claim 8 wherein the other way of entering the index comprised enabling the user to verbally spell the spoken name.

11. A method of automating telephone directory services for a telephone user having a display telephone as claimed in claim 7 wherein the steps of prompting, accepting, passing and assembling are accomplished by an access server which may be accessed by the user by dialing a predetermined telephone number.

12. A method of automating telephone directory services for a telephone user having a display telephone as claimed in claim 11 wherein the step of displaying is accomplished by passing the representations from the access server to the display telephone over a telephone line along with commands which enable the display telephone to display the representations as text for the user.

10. A method of automating telephone directory services for a telephone user having a display telephone as claimed 8 wherein the other way of entering the index comprises enabling the user to manually spell the spoken name using the dial pad of the display telephone.

13. Apparatus for improving the utility of speech recognition of words spoken by a speaker, comprising a server in a network enabled to receive voice and data signals over a voice grade connection in a switched telephone network, the server being programmed to prompted the speaker for spoken words which are received from the voice grade connection as voice signals and to pass the spoken words to a speech recognition algorithm which returns representations of the spoken words to the server;

the server being further enabled to pass the representations of the spoken words to a voice terminal with a display surface which displays the representations for the speaker to permit the speaker to select a correct representation of the spoken words to thus improve the utility of the speech recognition of the words.

14. Apparatus for improving the utility of speech recognition of words spoken by a speaker as claimed in claim 13 wherein the speech recognition algorithm resides on another server connected to the network.

15. Apparatus for improving the utility of speech recognition of words spoken by a speaker as claimed in claim 13 wherein the apparatus is used to provide automated telephone directory services and the spoken words are used as indicia for retrieving subscriber information from a telephone directory connected to a wide area network which may be accessed by the server.

16. Apparatus for improving the utility of speech recognition of words spoken by a speaker as claimed in claim 13 wherein the server may selectively pas words to an alpha speech recognition algorithm to enable the user to verbally spell a spoken name if a spoken version of the spoken name cannot be interpreted by the speech recognition algorithm.

17. A method of improving the utility of speech recognition of words spoken by a speaker, comprising:

a) capturing an electronic signal, using an Analog Display Services Interface (ADSI) telephone, representative of a word spoken by the speaker;

b) sending the electronic signal through the Public Switched Telephone Network (PSTN) to a speech recognition algorithm;

c) receiving via the PSTN from the speech recognition algorithm at least one representation of the word;

d) displaying on a display surface of the ADSI telephone the at least one representation of the word for the speaker, to permit the to select a correct representation of the word from among the at least one representation; and

e) repeating steps a)-c) in an event that none of the representations of the word are verified as correct, or enabling the speaker to communicate the at least one word using a key pad of the ADSI telephone.

18. The method as claimed in claim 17 wherein prior to step a), the speaker dials a predetermined number to access a server connected to the PSTN by a voice grade connection.

19. The method as claimed in claim 17 wherein the words spoken by a speaker is an index for retrieving a record of interest from a database.

20. The method as claimed in claim 19 wherein the database is one of a “

411”

database of residential telephone numbers;

a Yellow Pages database of the telephone numbers of business advertisers;

a database of business telephone numbers;

a database of toll free telephone numbers; and

, a global database which may include a variety of information respecting entities for which records exist.

21. Apparatus for improving the utility of speech recognition of words spoken by a speaker, comprising in combination:

a server in a network adapted to receive voice and data signals over a voice grade connection in a switched telephone network, the server being programmed to prompt the speaker for spoken words which are received via the voice grade connection as voice signals, and to pass the voice signals to a speech recognition algorithm that returns representations of, the spoken word to the server;

the server being further adapted to send the representations over the voice grade connection to an Analog Display Services Interface (ADSI) telephone, which displays the representation for the speaker to permit the speaker to select a correct representation of the spoken word to improve the utility of the speech recognition of the spoken words.

22. Apparatus as claimed in claim 21 wherein the server is further adapted to assemble a query using one or more of the words spoken by the speaker, and further adapted to send the query to a database to retrieve a record of interest.

23. Apparatus as claimed in claim 22 wherein the database is one of a “

411”

database of residential telephone numbers;

a Yellow Pages database of the telephone numbers of business advertisers;

a database of business telephone numbers;

a database of toll free telephone numbers; and

, a global database which may include a variety of information respecting entities for which records exist.

24. A method of automatically information retrieval from a database for a telephone user having an Analog Display Service Interface (ADSI) telephone, comprising the steps of:

a) prompting the user for spoken words used as indicia to locate information of interest in the database;

b) accepting at least one of the spoken words from the user;

c) passing an electronic representation of each spoken word to a speech recognition algorithm and accepting from the speech recognition algorithm at least one representation of the spoken word;

d) displaying as text on the ADSI telephone the at least one representation of the spoken word to permit the user to select a correct representation of the spoken word; and

e) assembling a query to the database after a correct representation of each spoken word has been selected by the user, in order to retrieve the information from the database.

25. The method as claimed in claim 24 wherein the database is a telephone directory services database.

26. The method as claimed in claim 25 wherein the database is one of a “

411”

database of residential telephone numbers;

a Yellow Pages database of the telephone numbers of business advertisers;

a database of business telephone numbers;

a database of toll free telephone numbers; and

, a global database which may include a variety of information respecting entities for which records exist.