Systems and methods for capturing and interpreting audio

Abstract

A device is provided as part of a system, the device being for capturing vibrations produced by an object such as a musical instrument. Via a fixation element, the device is fixed to a drum. The device has a sensor spaced apart from a surface of the drum, located relative to the drum, and a magnet adjacent the sensor. The fixation element transmits vibrations from its fixation point on the drum to the magnet. Vibrations from the surface of the drum and from the magnet are transmitted to the sensor. A method may further be provided for interpreting an audio input, such as the output of the sensors within the system, the method comprising identifying an audio event or grouping of audio events within audio data, generating a model of the audio event that includes a representation of a timbre characteristic, and comparing that representation to expected representations.

What is claimed is: 
     
         1 . A device for capturing vibrations produced by an object, the device comprising:
 a fixation element for fixing the device to an object;   a first sensor for detecting vibration of the object at the fixation element; and   a second sensor spaced apart from a surface of the object and located relative to the object.   
     
     
         2 . The device of  claim 1  wherein the object is a musical instrument. 
     
     
         3 . The device of  claim 2  wherein the second sensor is an optical sensor. 
     
     
         4 . The device of  claim 3  wherein the optical sensor is fixed relative to a visible target on a surface of the musical instrument. 
     
     
         5 . The device of  claim 1  wherein the musical instrument is a drum, and the fixation element transmits vibrations from a drum rim to the first sensor. 
     
     
         6 . A system for capturing vibrations produced by an object, the system comprising:
 a device for capturing vibrations produced by an object, the device comprising:
 a fixation element for fixing the device to an object; 
 a first sensor for detecting vibration of the object at the fixation element; and 
 a second sensor spaced apart from a surface of the object and located relative to the object, and 
   a processing unit for identifying at least one audio event based on signals captured at the first sensor.   
     
     
         7 . The system of  claim 6 , wherein the processing unit further comprises a signal input for receiving a signal from the device and an audio output for outputting an audio signal based on the audio event identified by the processor. 
     
     
         8 . The system of  claim 6 , wherein the device comprises a first housing and the processing unit comprises a second housing independent of the device. 
     
     
         9 . A method for extracting audio from electrical signals within a data processing device, the method comprising:
 receiving, at the data processing device, a stream of audio input data;   identifying, in the audio input data, at least one audio event;   generating, by the data processing device, an n-dimensional representation of the audio event;   classifying the audio event by comparing at least one dimension of the representation of the audio event to a corresponding dimension expected representations of a plurality of audio events.   
     
     
         10 . The method of  claim 9  further comprising identifying, in the audio input data, an onset of the audio event and selecting a discrete analysis window from the audio data based on the location of the onset of the audio event in the audio data, and wherein the n-dimensional representation is generated by evaluating the contents of the discrete analysis window. 
     
     
         11 . The method of  claim 9 , wherein the n-dimensional representation is compared geometrically to a plurality of audio zones defined by expected signal parameters in the at least one dimension, and wherein when the n-dimensional representation is within one of the audio zones, the audio event is classified in accordance with the corresponding audio zone. 
     
     
         12 . The method of  claim 9  further comprising:
 identifying a plurality of audio events; 
 generating an n-dimensional representation corresponding to each of the plurality of audio events, wherein at least one of the n dimensions of each representation corresponds to the at least one dimension; and 
 identifying a pattern by evaluating the plurality of audio events. 
 
     
     
         13 . The method of  claim 12  further comprising:
 identifying a subset of audio events of the plurality of audio events that are related based on their corresponding at least one dimension; and 
 identifying a pattern by evaluating only related audio events. 
 
     
     
         14 . The method of  claim 12  wherein the patterns identified represent a tempo of the plurality of audio events. 
     
     
         15 . The method of  claim 14  further comprising applying a delay, echo, or time-stretching effect to an audio output associated with the plurality of audio events. 
     
     
         16 . The method of  claim 12  further comprising:
 identifying, at a user interface, at least one expected pattern; and 
 recording, at a memory, a grouping of the n-dimensional representations corresponding to the plurality of audio events as an example of the at least one expected pattern. 
 
     
     
         17 . The method of  claim 12  further comprising:
 determining if the identified pattern corresponds to one of a plurality of expected trigger patterns; and 
 triggering an output event corresponding to the trigger pattern where the identified pattern corresponds to an expected trigger pattern. 
 
     
     
         18 . The method of  claim 9  further comprising recording, at a memory, the n-dimensional representation as an expected representation of the audio event. 
     
     
         19 . The method of  claim 9  further comprising;
 identifying, at a user interface, an expected audio event in the stream of audio input data; 
 confirming that the audio event corresponds to the expected audio event prior to recording, at a memory, the n-dimensional representation. 
 
     
     
         20 . The method of  claim 9 , wherein the at least one dimension represents a fundamental frequency or pitch of an audio event.
 receiving, at the data processing device, a stream of audio output data;   identifying, in the audio input data, an output event corresponding to the audio event in the audio output data; and   recording, at a memory, the output event as a sample output that may be associated with the identified audio event.