System and method for providing remote automatic speech recognition and text-to-speech services via a packet network

• US 6,856,960 B1
• Filed: 01/21/2003
• Issued: 02/15/2005
• Est. Priority Date: 04/14/1997
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: Sharp, Robert Douglas, Dragosh, Pamela Leigh, Roe, David Bjorn
• Primary Examiner(s): Azad, Abul K.
• Application Number:
  US10/347,977
• Time in Patent Office: 756 Days
• Field of Search: 704/270.1, 704/243, 704/251, 704/231, 704/235, 704/260, 704/255, 704/275, 704/270, 704/257
• US Class Current: 704/270.1
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• 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
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• CPC Class Codes: H04M 7/006 Networks other than PSTN/ISDN providing telephone service, e.g. Voice over Internet Protocol (VoIP) , including next generation networks with a packet-switched transport layer H04L65/00 takes precedence; aspects not specific to the type of network H04M3/00; special services in those networks H04M3/42

Abstract

A system and method of operating an automatic speech recognition service using a client-server architecture is used to make automatic speech recognition (ASR) and text to speech (TTS) services accessible at a client location remote from the location of the main ASR and TTS engines. The present invention utilizes client-server communications over a packet network, such as the Internet or a wireless network, where the ASR/TTS server receives a grammar from the client or selects from a locally second plurality of grammars, receives information representing speech from the client, performs speech recognition, and returns information based upon the recognized speech to the client.

Claims

1. A method of operating an automatic speech recognition service remotely accessible by a client over an Internet Protocol Network, the method comprising:

(a) receiving from the client a grammar identifier;

(b) using the grammar identifier, selecting a grammar used for recognizing the speech information from a plurality of grammars;

(c) receiving from the client speech information;

(d) using the selected grammar, recognizing the received speech information by applying an automatic speech recognition algorithm; and

(e) sending information based on the recognized speech over the Internet Protocol network to the client.

2. The method of operating an automatic speech recognition service remotely accessible by a client of claim 1, wherein the plurality of grammars is stored local to the automatic speech recognition service.

3. The method of operating an automatic speech recognition service remotely accessible by a client of claim 1, wherein the plurality of grammars is stored remotely from the automatic speech recognition service.

4. The method of operating an automatic speech recognition service remotely accessible by a client of claim 3, wherein the grammar identifier is a uniform resource locator-compatible address.

5. A method of operating a spoken dialog service remotely accessible by a client over an Internet Protocol network, the method comprising:

(a) receiving from the client a grammar identifier;

(b) using the grammar identifier, selecting a grammar used for recognizing the speech information from a plurality of grammars;

(c) receiving from the client speech information;

(d) using the selected grammar recognizing the received speech information by applying an automatic speech recognition algorithm; and

(e) transmitting speech from the spoken dialog service based on the recognized speech information over the Internet Protocol network to the client.

6. The method of operating a spoken dialog service remotely accessible by a client of claim 5, wherein the plurality of grammar are stored local to the spoken dialog service.

7. The method of operating a spoken dialog service remotely accessible by a client of claim 5, wherein the plurality of grammars are stored remotely from the spoken dialog service.

8. The method of operating a spoken dialog service remotely accessible by a client of claim 7, wherein the grammar identifier is a uniform resource locator-compatible address.

9. A method of operating a spoken dialog service remotely accessible by a client over an Internet Protocol network, the method comprising, at the client:

(a) receiving speech information from a user;

(b) transmitting the speech information to a server for speech recognition;

(c) transmitting to the server a grammar identifier, wherein the server may use the grammar identifier to select a grammar from a plurality of grammars; and

(d) receiving generated speech from the server in response to the recognized user speech information over the Internet Protocol network.

10. The method of operating a spoken dialog service remotely accessible by a client of claim 9, wherein the plurality of grammars is stored local to the server.

11. The method of operating a spoken dialog service remotely accessible by a client of claim 9, wherein the plurality of grammars is stored remotely from the server.

12. The method of operating a spoken dialog service remotely accessible by a client of claim 11, wherein the grammar identifier is a uniform resources locator-compatible address.