Acoustic Event Detection and Data Storage

Abstract

An analysis system has at least one monitoring assembly that includes at least one microphone to monitor an acoustic field proximate the monitoring assembly. The at least one microphone produces at least one microphone signal responsive to the acoustic field. The analysis system further includes a data storage device configured to buffer the at least one microphone signal and an audio analysis system configured to analyze a content of the data storage device where the audio analysis system is configured to analyze the content of the buffer to process at least a sound into a response or action.

1 . A system comprising:
 a first ambient sound microphone, the first ambient sound microphone producing a first ASM signal;   a second ambient sound microphone, the second ambient sound microphone producing a second ASM signal;   an ear canal microphone, the ear canal microphone producing an ear canal signal, wherein the first ambient sound microphone, the second ambient sound microphone, and the ear canal microphone are part of an earphone;   a first circular buffer, wherein the first ambient sound signal is constantly recorded in the circular buffer during a mode operation of the earphone;   a second circular buffer, wherein the second ambient sound signal is constantly recorded in the second circular buffer during the mode operation of the earphone;   a third circular buffer, wherein the ear canal signal is constantly recorded in the third circular buffer during the mode operation of the earphone, wherein the mode operation of the earphone is when a user activates a mode of operation where the first ambient sound signal, the second ambient sound signal and the ear canal sound signal are all constantly recorded;   a data storage system; and   an event detector, wherein when an event is detected the event detector retrieves data from the circular buffer, embeds a time stamp into the data generating a new data, and stores the new data to the data storage system, wherein the data includes at least one of the first ambient sound signal, the second ambient sound signal, audio content, or the ear canal sound signal.   
     
     
         2 . The system of  claim 1 , wherein the data includes the first ambient sound signal and the ear canal signal. 
     
     
         3 . The system of  claim 1 , wherein the data includes the first ambient sound signal and the second ambient sound signal. 
     
     
         4 . The system of  claim 1 , wherein the data includes the second ambient sound signal and the ear canal signal. 
     
     
         5 . The system of  claim 1 , wherein the event is at least one of breaking glass, an accident, a gun shot, a keyword, hand-clap, a whistle, or a user's voice or a combination thereof. 
     
     
         6 . The system of  claim 1 , wherein the audio content is at least one of a signal from a personal media player, or a signal from phone, or a warning signal or a combination thereof. 
     
     
         7 . The system according to  claim 1  further comprising:
 an audio forensics analysis system configured to analyze either a content of one or more of the first circular buffer, the second circular buffer or the third circular buffer, or wherein the analysis system is configured to analyze the new data stored on the data storage device. 
 
     
     
         8 . The system according to  claim 7 , where the audio forensics analysis system includes a communication system configured to transmit the content of at least one or more of the first circular buffer, the second circular buffer or the third circular buffer or the new data of the data storage device to a remote server for analysis. 
     
     
         9 . The system according to  claim 8 , wherein the analysis is to determine if speech is present in the content. 
     
     
         10 . The system according to  claim 9 , wherein if speech is present in the content then a first remote server converts the speech to text and either the first remote server sends the results to the system or a second remote server sends the results to the system. 
     
     
         11 . The system according to  claim 1 , wherein the system is at least one of a phone, a computing device or a personal media player or a combination thereof. 
     
     
         12 . The system according to  claim 10 , further including:
 a text-to-speech translation system to translate the received results from the first or second remote server into speech.   
     
     
         13 . The system according to  claim 1 , wherein the first circular buffer and the second circular buffer and the third circular buffer can each share a portion of memory in the system. 
     
     
         14 . The system according to  claim 5 , wherein when the accident is determined the system automatically transmits an indication to a remote location a message that a user has been involved in the accident. 
     
     
         15 . A method comprising:
 receiving a first sound signal, wherein the first sound signal is generated by a first microphone;   receiving a second sound signal, wherein the second sound signal is generated by a second microphone;   receiving a third sound signal, wherein the third sound signal is generated by a third microphone, wherein the first microphone and the second microphone and the third microphone are part of a device;   constantly recording the first sound signal in a first circular buffer;   constantly recording the second sound signal in a second circular buffer;   constantly recording the second sound signal in a third circular buffer;   analyzing the first circular buffer for a first event and if a first event is detected then storing the first circular buffer into a data storage system, wherein the first circular buffer is part of a memory that is part of the device, wherein the second circular buffer is part of a second memory that is part of the device, wherein the third circular buffer is part of a third memory that is part of the device, and wherein the data storage system can be part of the device or part of a remote device;   analyzing the second circular buffer for second event and if a second event is detected then storing the second circular buffer into the data storage system; and   analyzing the third circular buffer for a third event and if a second event is detected then storing the second circular buffer into the data storage system.   
     
     
         16 . The method of  claim 15 , wherein the first event is at least one of breaking glass, an accident, a gun shot, a keyword, hand-clap, a whistle, or a user's voice or a combination thereof. 
     
     
         17 . The method of  claim 16 , wherein the first circular buffer is the same as the second circular buffer. 
     
     
         18 . The method according to  claim 16 , wherein the first event, the second event and the third event are the same event that is being detected. 
     
     
         19 . The method according to  claim 16 , wherein the device is at least one of an earphone, a phone, a computational device, or a personal media player or a combination thereof. 
     
     
         20 . The method according to  claim 15 , wherein the data storage device is part of a remote device, wherein the method further includes:
 analyzing data in the data storage device to detect speech, wherein the remote device does the analysis, and if speech is detected then the remote device converts the speech to words, and the words are sent back to the device.