Distinguishing speech from multiple users in a computer interaction

Abstract

Speech from multiple users is distinguished. In one example, an apparatus has a sensor to determine a position of a speaker, a microphone array to receive audio from the speaker and from other simultaneous audio sources, and a processor to select a pre-determined filter based on the determined position and to apply the selected filter to the received audio to separate the audio from the speaker from the audio from the other simultaneous audio sources.

1 . (canceled) 
     
     
         2 . A method, comprising:
 receiving, via a microphone array including a plurality of microphones, a plurality of sounds including at least a first speaker sound from a first speaker;   determining a time difference between a first time of receipt of the plurality of sounds at a first microphone and a second time of receipt of the plurality of sounds at a second microphone, the first and second microphones included in the microphone array;   determining a position of the first speaker based at least in part on the time difference; and   determining a first filter based at least in part on the position of the first speaker;   wherein the first filter is to separate the first speaker sound from the plurality of sounds.   
     
     
         3 . The method of  claim 2 , comprising:
 determining a position of a second speaker based at least in part on the time difference; and   determining a second filter based at least on the position of the second speaker, wherein:
 the plurality of sounds includes a second speaker sound from the second speaker; and 
 the second filter is to separate the second speaker sound from the plurality of sounds. 
   
     
     
         4 . The method of  claim 2 , comprising:
 transcribing the first speaker sound.   
     
     
         5 . The method of  claim 2 , comprising:
 storing the first filter in a table; and   associating the stored filter with the position of the first speaker.   
     
     
         6 . A system, comprising:
 a microphone array including a plurality of microphones; and   one or more processors to execute instructions to:
 receive, via the microphone array, a plurality of sounds including at least a first speaker sound from a first speaker; 
 determine a time difference between a first time of receipt of the plurality of sounds at a first microphone and a second time of receipt of the plurality of sounds at a second microphone, the first and second microphones included in the microphone array; 
 determine a position of the first speaker based at least in part on the time difference; and 
 determine a first filter based at least in part on the position of the first speaker; 
 wherein the first filter is to separate the first speaker sound from the plurality of sounds. 
   
     
     
         7 . The system of  claim 6 , wherein:
 the one or more processors are further to execute instructions to:
 determine a position of a second speaker based at least in part on the time difference; and 
 determine a second filter based at least on the position of the second speaker; 
   the plurality of sounds includes a second speaker sound from the second speaker; and   the second filter is to separate the second speaker sound from the plurality of sounds.   
     
     
         8 . The system of  claim 6 , wherein the one or more processors are further to execute instructions to transcribe the first speaker sound. 
     
     
         9 . The system of  claim 6 , wherein the one or more processors are further to execute instructions to:
 store the first filter in a table; and   associate the stored filter with the position of the first speaker.   
     
     
         10 . One or more non-transitory computer-readable storage devices having stored thereon instructions which, when executed by one or more processors, result in operations comprising:
 receive, via a microphone array including a plurality of microphones, a plurality of sounds including at least a first speaker sound from a first speaker;   determine a time difference between a first time of receipt of the plurality of sounds at a first microphone and a second time of receipt of the plurality of sounds at a second microphone, the first and second microphones included in the microphone array;   determine a position of the first speaker based at least in part on the time difference; and   determine a first filter based at least in part on the position of the first speaker;   wherein the first filter is to separate the first speaker sound from the plurality of sounds.   
     
     
         11 . The one or more non-transitory computer-readable storage devices of  claim 10 , wherein the instructions comprise instructions which, when executed by the one or more processors, result in operations comprising:
 determine a position of a second speaker based at least in part on the time difference; and   determine a second filter based at least on the position of the second speaker, wherein:
 the plurality of sounds includes a second speaker sound from the second speaker; and 
 the second filter is to separate the second speaker sound from the plurality of sounds. 
   
     
     
         12 . The one or more non-transitory computer-readable storage devices of  claim 10 , wherein the instructions comprise instructions which, when executed by the one or more processors, result in operations comprising:
 transcribe the first speaker sound.   
     
     
         13 . The one or more non-transitory computer-readable storage devices of  claim 10 , wherein the instructions comprise instructions which, when executed by the one or more processors, result in operations comprising:
 store the filter in a table; and   associate the stored filter with the position of the first speaker.