Alarm Method And System Based On Voice Events, And Building Method On Behavior Trajectory Thereof

• US 20100127878A1
• Filed: 02/06/2009
• Published: 05/27/2010
• Est. Priority Date: 11/26/2008
• Status: Active Grant

• Current Assignee: Industrial Technology Research Institute
• Original Assignee: Industrial Technology Research Institute
• Inventors: Chiu, Yu-Hsien, Yan, Gwo Lang, Wang, Yuh-Ching
• Granted Patent: US 8,237,571 B2
• Time in Patent Office: Days
• US Class Current: 340/573.100
• CPC Class Codes: G08B 13/1672 using sonic detecting means, e.g. a microphone operating in the audio frequency range
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices

Abstract

Disclosed are an alarm method and system based on voice events, and a building method on behavior trajectory thereof The system comprises a signal sensor, a voice-event detector and notice and alarm element. In the method, voice signals are captured from a remote unit in an environment. The captured voice signals are classified into at least a voice event. As such, an emergent-event notice is automatically transmitted out if one of predefined emergent events is detected. In the building method on behavior trajectory, messages on voice events are continuously recorded. When the number of the recorded voice events reaches a threshold, a behavior trajectory is constructed, in which a behavior consists of two or more voice events or a single voice event.

Claims

1. An alarm method based on voice events, said method comprising:

capturing a plurality voice signal of an environment where a remote unit being located;

classifying said captured voice signals into at least a voice event by using a voice event detection method; and

issuing a notification alarm message actively when said at least a voice event being a pre-defined emergency event.

2. The method as claimed in claim 1, said method further includes:

integrating said captured voice signals with other sensed signals to detect voice events, continuously recording detected voice events, and issuing a notification alarm message when detecting an emergency event.

3. The method as claimed in claim 1, wherein said voice event detection method at least includes:

performing voice endpoint detection on said captured voice signals to obtain a plurality of voice segments;

capturing characteristic parameter of each said voice segment; and

comparing said characteristic parameter of said voice segment with pre-stored characteristic parameter for voice signal comparison to determine a corresponding voice event type.

4. The method as claimed in claim 1, said method further includes an abnormal behavior decision method to continuously determine whether a latest behavior being an abnormal behavior or not, wherein a behavior consisting of a single voice event, or two or more voice events.

5. The method as claimed in claim 4, wherein said abnormal behavior decision method further includes:

continuously detecting latest voice events through said voice event detection method and continuously recording the detected voice events;

generating a behavior trajectory through a behavior trajectory building method after accumulating a sufficient number of voice events;

detecting a latest behavior through the latest continuous voice events and comparing said latest behavior with history of said behavior trajectory; and

issuing a notification and alarm message when detecting an abnormal behavior.

6. The method as claimed in claim 1, said method further includes a behavior trajectory building method for generating a behavior trajectory.

7. The method as claimed in claim 6, wherein said behavior trajectory building method at least includes:

naming said detected voice events with letters to obtain a plurality of letter sequences representing said detected voice events;

comparing pair-wise said plurality of letter sequences to find at least an identical string;

computing presence probability and length of said at least an identical strings and setting thresholds for said probability and said length to obtain at least a qualified pre-selected string;

categorizing said at least a pre-selected string into a plurality of types, with each type representing a behavior type, by using a classification algorithm; and

inducing said at least a qualified pre-selected string of each type to build a behavior trajectory.

8. The method as claimed in claim 1, wherein said voice event detection method further includes the detection of the time and location of said at least a voice event and recording the time and location of said at least a voice event.

9. The method as claimed in claim 1, wherein a voice able to trigger said emergency event is a human meaningless involuntary voice or a meaningful voice indicating a human bumping wall, floor or other objects.

10. The method as claimed in claim 8, wherein the location of said at least a voice event is within a closed living space.

11. A method for building behavior trajectory, comprising:

continuously detecting latest voice events by using a voice event detection method and continuously record the detected voice events;

naming the detected voice events with letters to obtain a plurality of letter sequences representing the detected voice events;

comparing pair-wise said letter sequences to find at least an identical string;

computing presence probability and length of said at last an identical strings and setting thresholds for the probability and length to obtain at least a qualified pre-selected string;

categorizing said at least a pre-selected string into types, with each said type representing a behavior type, by using a classification algorithm; and

inducing said at least a qualified pre-selected string of each type to build a behavior trajectory.

12. The method as claimed in claim 11, wherein said voice event detection method classifies a plurality of captured voice signals into at least one voice event.

13. An alarm system based on voice events, said system comprising:

a signal sensor for capturing one or more voice signals externally inputted, outputting said sensed signals and recording the locations of said signals;

a voice event detector connected to said signal sensor, for determining a plurality of corresponding voice events based on said locations and at least a characteristic parameter of said sensed signals; and

a notice and alarm element connected to said voice event detector, for executing notification and alarming functions based on said plural voice events.

14. The system as claimed in claim 13, said system further includes a behavior trajectory building module for continuously recording voice events, and inducing a behavior trajectory after accumulating a sufficient number of voice events, wherein a behavior consists of a single voice event or two or more voice events.

15. The system as claimed in claim 13, said system further includes an abnormal behavior decision module for continuously detecting latest behavior, comparing against a history of behavior trajectory, and issuing an abnormal behavior alarm when detecting an abnormal behavior.

16. The system as claimed in claim 13, said system is integrated with a toilet, and said signal sensor further captures pressure signal and switch signal triggered by flushing switch or seat of said toilet.

17. The system as claimed in claim 13, said system is integrated with a bed mattress, and said signal sensor further captures pressure signal, switch signal, temperature signal humidity signal or physiological signal triggered by human or objects on said bed mattress.

18. The system as claimed in claim 13, said system is integrated with a ceiling, and said signal sensor further captures at least an ultrasonic distance-measuring signal from an ultrasonic distance-measuring device installed on said ceiling.

19. The system as claimed in claim 13, said system is integrated with a faucet, and said signal sensor further captures pressure signal or switch signal triggered by switch of said faucet.

20. The system as claimed in claim 13, said system is integrated with a wheelchair, and said signal sensor further captures pressure signal or switch signal triggered by cushion, wheel or brake switch of said wheelchair.

21. The system as claimed in claim 13, said system is integrated with a door or a window, and said signal sensor further captures pressure signal or switch signal triggered by opening and closing said door or said window.

22. The system as claimed in claim 13, wherein a voice able to trigger said emergency event is a human meaningless involuntary voice or a meaningful voice indicating a human bumping wall, floor or other objects.

23. The system as claimed in claim 13, wherein said voice event is an ordinary voice event or an emergency event.

24. The system as claimed in claim 13, wherein said specific living space is chosen from a group consisting of bathroom, hospital room, household bedroom and living room.

25. The system as claimed in claim 23, wherein said emergency event is a pre-defined event selected from the events triggered by the voices of falling during getting in or off bed, falling during getting or off wheelchair, trip or slip when walking, choking when drinking, temporarily stopping breathing, fight or argument, crying or moaning, calling or calling for help, sudden illness attack, wrecking, breaking or falling object, unable to finish the use of toilet, and entering a dangerous zone.

26. The system as claimed in claim 23, wherein said ordinary voice event is an event selected from the events triggered by the voices of walking or movement, getting in or off bed, getting in or off wheelchair, opening or closing door, using faucet, using toilet, flushing toilet, drinking water.