DISTINGUISHING SPEECH FROM MULTIPLE USERS IN A COMPUTER INTERACTION

• US 20180293049A1
• Filed: 11/14/2017
• Published: 10/11/2018
• Est. Priority Date: 07/21/2014
• Status: Active Application

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Gupta, Ram Mohan, Cordourier Maruri, Hector A., Beltman, Willem M.
• Application Number:
  US15/812,794
• Publication Number:
  US 20180293049A1
• Time in Patent Office: Days
• CPC Class Codes: G06F 3/165 Management of the audio stream, e.g. setting of volume, audio stream path
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2021/02166 Microphone arrays; Beamforming
• CPC Class Codes: G10L 21/0272 Voice signal separating
• CPC Class Codes: H04R 1/406 microphones
• CPC Class Codes: H04R 2430/25 Array processing for suppression of unwanted side-lobes in directivity characteristics, e.g. a blocking matrix

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.

Claims

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.