Method and apparatus for speech recognition for distinguishing non-speech audio input events from speech audio input events

• US 5,764,852 A
• Filed: 08/16/1994
• Issued: 06/09/1998
• Est. Priority Date: 08/16/1994
• Status: Expired due to Term

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Williams, Marvin L.
• Primary Examiner(s): MacDonald, Allen R.
• Assistant Examiner(s): COLLINS, ALPHONSO
• Application Number:
  US08/291,372
• Time in Patent Office: 1,393 Days
• Field of Search: 395/2, 395/2.4, 395/2.42, 395/2.35, 395/2.36, 395/2.37, 395/2.52, 395/2.6, 395/2.64, 395/2.79, 395/2.8, 395/2.81, 395/2.84, 395/41, 395/43, 395/46, 395/47
• US Class Current: 704/243
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10

Abstract

A method and apparatus for analyzing audio input events. A template is utilized to analyze audio input events. A speech audio input event is identified. The identified speech audio input event is recorded. The recorded speech audio input event is processed to create a first entry in a template. A selected non-speech audio input event which occurs in a selected environment is identified. The identified non-speech audio input event is recorded. Then the recorded non-speech audio input event is processed to create a second entry in the template. Thereafter, a speech audio input event and a non-speech audio input event is distinguished by comparing an audio input event to the template.

Claims

1. A method for analyzing audio input events in a data processing system, wherein said data processing system utilizes a template to analyze audio input events, wherein said data processing system includes a peripheral device that generates said audio input event and an interrupt, said method comprising the steps of:

identifying a speech audio input event;

recording said identified speech audio input event;

processing said recorded speech audio input event to create a first entry in a template;

identifying a selected non-speech audio input event which occurs in a selected environment;

recording said identified non-speech audio input event;

processing said recorded non-speech audio input event to create a second entry in said template; and

thereafter, distinguishing between a speech audio input event and a non-speech audio input event by comparing said audio input event to said template in response to detecting said interrupt and detecting said audio input event within a preselected amount of time wherein said non-speech audio input event is identified.

2. The method of claim 1, further comprising:

determining whether a command is associated with said non-speech audio input event in response to identification said non-speech audio input event; and

responsive to said command being associated with said non-speech audio input event, executing said command.

3. A method for analyzing audio input events in a data processing system, wherein said data processing system utilizes a template to analyze audio input events and wherein said data processing system includes a peripheral device that generates an audio input event and an interrupt, said method comprising the steps of:

identifying a speech audio input event;

recording said identified speech audio input event;

processing said recorded speech audio input event to create a first entry in a template;

identifying a selected non-speech audio input event which occurs in a selected environment;

recording said identified non-speech audio input event;

processing said recorded non-speech audio input event to create a second entry in said template for said processed non-speech audio input event;

detecting an interrupt;

detecting said audio input event, wherein said audio input event occurs after said interrupt;

identifying a non-speech audio input event by comparing an audio input event to said template;

responsive to identifying a non-speech audio input event occurring a preselected amount of time after said interrupt occurs, determining whether a command is associated with said non-speech audio input event; and

executing said command in response to said command being associated with said non-speech audio input event.

4. The method of claim 3 further comprising processing said identified non-speech audio input event occurring said preselected amount of time after said interrupt occurs to replace said second entry in said template for said processed non-speech audio input event.

5. An apparatus for analyzing audio input events, wherein said utilizes a template to analyze audio input events, wherein apparatus includes a peripheral device that generates an audio input event and an interrupt, said apparatus comprising:

first identification means for identifying a speech audio input event;

first recording means for recording said identified speech audio input event;

first processing means for processing said recorded speech audio input event to create a first entry in a template;

second identification means for identifying a selected non-speech audio input event which occurs in a selected environment;

second recording means for recording said identified non-speech audio input event;

second processing means for processing said recorded non-speech audio input event to create a second entry in said template for said processed non-speech audio input event; and

comparison means for distinguishing between a speech audio input event and a non-speech audio input event by comparing said audio input event to said template in response to detecting said interrupt and detecting said audio input event within a preselected amount of time, wherein said non-speech audio input events may be efficiently distinguished from speech audio input events.

6. The apparatus of claim 5, further comprising:

means for determining whether a command is associated with said non-speech audio input event in response to identification of said non-speech audio input event; and

responsive to said command being associated with said non-speech audio input event, means for executing said command.

7. An apparatus method for analyzing audio input events, where said apparatus utilizes a template to analyze audio input events and wherein said data processing system includes a peripheral device that generates an audio input event and an interrupt, said apparatus comprising:

first identification means for identifying a speech audio input event;

first recording means for recording said identified speech audio input event;

first processing means for processing said recorded speech audio input event to create a first entry in a template;

second identification means for identifying a selected non-speech audio input event which occurs in a selected environment;

second recording means for recording said identified non-speech audio input event;

second processing means for processing said recorded non-speech audio input event to create a second entry in said template for said processed non-speech audio input event;

first detection means for detecting an interrupt;

second detection means for detecting said audio input event, wherein said audio input event occurs after said interrupt;

third identification means for identifying a non-speech audio input event by comparing an audio input event to said template;

determination means, responsive to identifying a non-speech audio input event occurring a preselected amount of time after said interrupt occurs, for determining whether a command is associated with said non-speech audio input event; and

execution means for executing said command in response to said command being associated with said non-speech audio input event.

8. The apparatus of claim 7 further comprising means for processing said identified non-speech audio input event occurring said preselected amount of time after said interrupt occurs to replace said second entry in said template for said processed non-speech audio input event.