Method and system for location-specific speech recognition

• US 5,524,169 A
• Filed: 12/30/1993
• Issued: 06/04/1996
• Est. Priority Date: 12/30/1993
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Incorporated (International Business Machines Corporation)
• Inventors: Miller, Roger M., Lucassen, John M., Cohen, Paul S., Sherwin, Elton B. Jr.
• Primary Examiner(s): MacDonald, Allen R.
• Assistant Examiner(s): ONKA, THOMAS
• Application Number:
  US08/175,701
• Time in Patent Office: 887 Days
• Field of Search: 395/2.4, 395/2.52, 395/2.53, 395/2.61, 395/2.64, 395/2.86, 395/2.79, 364/424.01, 364/424.02
• US Class Current: 704/231
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/28 Constructional details of speech recognition systems
• CPC Class Codes: G10L 2015/226 using non-speech characteristics
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A method and system for reducing perplexity in a speech recognition system based upon determined geographic location. In a mobile speech recognition system which processes input frames of speech against stored templates representing speech, a core library of speech templates is created and stored representing a basic vocabulary of speech. Multiple location-specific libraries of speech templates are also created and stored, each library containing speech templates representing a specialized vocabulary for a specific geographic location. The geographic location of the mobile speech recognition system is then periodically determined utilizing a cellular telephone system, a geopositioning satellite system or other similar systems and a particular one of the location-specific libraries of speech templates is identified for the current location of the system. Input frames of speech are then processed against the combination of the core library and the particular location-specific library to greatly enhance the accuracy and efficiency of speech recognition by the system. Each location-specific library preferably includes speech templates representative of location place names, proper names, and business establishments within a specific geographic location.

Claims

1. A method for enhancing the efficiency of a mobile speech recognition system which processes input frames of speech against stored templates representing speech, said method comprising the steps of:

creating and storing a core library of speech templates representing a basic vocabulary of speech;

creating and storing a plurality of location-specific libraries of speech templates, each representing a specialized vocabulary for a particular geographic location;

determining a geographic location of said mobile speech recognition system;

combining said core library of speech templates with a particular one of said plurality of location-specific libraries of speech templates in response to said determination of said geographic location of said mobile speech recognition system; and

processing input frames of speech against said combined core library and location-specific library.

2. The method for enhancing the efficiency of a mobile speech recognition system according to claim 1, wherein said step of determining a geographic location of said mobile speech recognition system comprises the step of utilizing a cellular telephone system to determine a geographic location of said mobile speech recognition system.

3. The method for enhancing the efficiency of a mobile speech recognition system according to claim 1, wherein said step of determining a geographic location of said mobile speech recognition system comprises the step of utilizing a geopositioning satellite system receiver to determine a geographic location of said mobile speech recognition system.

4. A mobile speech recognition system comprising:

an audio input means for receiving input speech;

memory;

a core library of speech templates stored within said memory representing a basic vocabulary of speech;

a plurality of location-specific libraries of speech templates stored within said memory, each representing a specialized vocabulary for a particular geographic location;

location determination means for determining a geographic location of said mobile speech recognition system;

library selection means coupled to said memory and said location determination means for selecting a particular one of said plurality of location-specific libraries in response to a determination of said geographic location of said mobile speech recognition system; and

speech processor means coupled to said audio input means and said memory for processing input speech frames against said core library and said particular one of said plurality of location-specific libraries wherein efficiency of speech recognition is enhanced.

5. The mobile speech recognition system according to claim 4, wherein said audio input means comprises a microphone.

6. The mobile speech recognition system according to claim 4, wherein said location determination means comprises a cellular telephone transceiver.

7. The mobile speech recognition system according to claim 4, wherein said location determination means comprises a global positioning satellite receiver.

8. The mobile speech recognition system according to claim 4, wherein said speech processor means includes an analog-to-digital converter.

9. The mobile speech recognition system according to claim 8, wherein said speech processor means comprises a personal computer.

10. The mobile speech recognition system according to claim 4, wherein each of said plurality of location-specific libraries of speech templates comprises a plurality of templates each representative of a plurality of location place names.