Audio watermark encoding/decoding

Abstract

A system may embed audio watermarks in audio data using an Eigenvector matrix. The system may detect audio watermarks in audio data despite the effects of reverberation. For example, the system may embed multiple repetitions of an audio watermark before generating output audio using loudspeaker(s). To detect the audio watermark in audio data generated by a microphone, the system may perform a self-correlation that indicates where the audio watermark is repeated. In some examples, the system may encode the audio watermark using multiple repetitions of a multi-segment Eigenvector. Additionally or alternatively, the system may encode the audio watermark using a binary sequence of positive and negative values, which may be used as a shared key for encoding/decoding the audio watermark. The audio watermark can be embedded in output audio data to enable wakeword suppression (e.g., avoid cross-talk between devices) and/or local signal transmission between devices in proximity to each other.

1 .- 20 . (canceled) 
     
     
         21 . A system comprising:
 at least one processor; and   at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
 cause a first device to output audio corresponding to watermarked media data, the watermarked media data representing media content and an audio watermark; 
 receive, from a second device and by at least one third device, first data corresponding to detection, by the second device, of the audio corresponding to the watermarked media data; 
 process the first data by the at least one third device to determine an action to be performed in response to detection of the audio watermark; and 
 cause the action to be performed. 
   
     
     
         22 . The system of  claim 21 , wherein the first data comprises audio data and the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
 process the audio data by the at least one third device to determine that the audio data includes a representation of the audio watermark.   
     
     
         23 . The system of  claim 21 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
 determine, by the second device, audio data representing the audio detected by the second device;   process, by the second device, the audio data to determine a representation of the audio watermark; and   in response to determining the representation of the audio watermark, send the first data from the second device to the at least one third device.   
     
     
         24 . The system of  claim 21 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
 determine media data corresponding to the media content;   determine second data corresponding to the audio watermark; and   create the watermarked media data by encoding the media data with the second data.   
     
     
         25 . The system of  claim 24 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
 cause the watermarked media data to be sent to the first device.   
     
     
         26 . The system of  claim 24 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
 store an association between the media data and the watermarked media data.   
     
     
         27 . The system of  claim 21 , wherein the action to be performed comprises output of second audio and wherein at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
 send, from the at least one third device to the second device a signal causing the second device to output the second audio.   
     
     
         28 . The system of  claim 21 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
 cause the second device to perform the action.   
     
     
         29 . The system of  claim 21 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
 determine, using a database, that the audio watermark corresponds to the action to be performed.   
     
     
         30 . The system of  claim 21 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
 store, by a storage associated with the at least one third device, an association between the audio watermark and at least one of the first device or second device.   
     
     
         31 . A computer-implemented method, comprising:
 causing a first device to output audio corresponding to watermarked media data, the watermarked media data representing media content and an audio watermark;   receiving, from a second device and by at least one third device, first data corresponding to detection, by the second device, of the audio corresponding to the watermarked media data;   processing the first data by the at least one third device to determine an action to be performed in response to detection of the audio watermark; and   causing the action to be performed.   
     
     
         32 . The computer-implemented method of  claim 31 , wherein the first data comprises audio data and wherein the method further comprises:
 processing the audio data by the at least one third device to determine that the audio data includes a representation of the audio watermark.   
     
     
         33 . The computer-implemented method of  claim 31 , further comprising:
 determining, by the second device, audio data representing the audio detected by the second device;   processing, by the second device, the audio data to determine a representation of the audio watermark; and   in response to determining the representation of the audio watermark, sending the first data from the second device to the at least one third device.   
     
     
         34 . The computer-implemented method of  claim 31 , further comprising:
 determining media data corresponding to the media content;   determining second data corresponding to the audio watermark; and   creating the watermarked media data by encoding the media data with the second data.   
     
     
         35 . The computer-implemented method of  claim 34 , further comprising:
 causing the watermarked media data to be sent to the first device.   
     
     
         36 . The computer-implemented method of  claim 34 , further comprising:
 storing an association between the media data and the watermarked media data.   
     
     
         37 . The computer-implemented method of  claim 31 , wherein the action to be performed comprises output of second audio and wherein the method further comprises:
 sending, from the at least one third device to the second device a signal causing the second device to output the second audio.   
     
     
         38 . The computer-implemented method of  claim 31 , further comprising:
 causing the second device to perform the action.   
     
     
         39 . The computer-implemented method of  claim 31 , further comprising:
 determining, using a database, that the audio watermark corresponds to the action to be performed.   
     
     
         40 . The computer-implemented method of  claim 31 , further comprising:
 storing, by a storage associated with the at least one third device, an association between the audio watermark and at least one of the first device or second device.