Adaptive filtering with machine learning

• US 9,769,553 B2
• Filed: 01/26/2016
• Issued: 09/19/2017
• Est. Priority Date: 11/25/2015
• Status: Active Grant

• Current Assignee: Dolby Laboratories Licensing Corporation (Dolby Laboratories Incorporated)
• Original Assignee: Doppler Labs, Inc.
• Inventors: Klimanis, Gints, Jaffe, Matthew J., Kraft, Noah, Lanman, III, Richard Fritz, Baker, Jeff
• Primary Examiner(s): Goins, Davetta W
• Assistant Examiner(s): Ojo, Oyesola C
• Application Number:
  US15/007,044
• Publication Number:
  US 20170150268A1
• Time in Patent Office: 602 Days
• Field of Search: 381 18
• CPC Class Codes: G06F 16/68 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/686 using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
• CPC Class Codes: G06F 16/687 using geographical or spatial information, e.g. location
• CPC Class Codes: G06F 3/165 Management of the audio stream, e.g. setting of volume, audio stream path
• CPC Class Codes: H04L 67/30 Profiles
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04R 1/1083 Reduction of ambient noise active noise reduction per se G10K11/175; protective devices for the ear, e.g. providing acoustic protection A61F11/06
• CPC Class Codes: H04R 2420/07 Applications of wireless loudspeakers or wireless microphones
• CPC Class Codes: H04R 2460/07 Use of position data from wide-area or local-area positioning systems in hearing devices, e.g. program or information selection
• CPC Class Codes: H04W 4/02 Services making use of location information
• CPC Class Codes: H04W 4/025 using location based information parameters

Abstract

Personal audio systems and methods are disclosed. A personal audio system includes a processor to generate a personal audio stream by processing the digitized ambient audio in accordance with an active processing parameter set, an event detector to detect a trigger event other than manual selection by a user of the personal audio system, and a controller configured to, in response to detection of the trigger event, select a new processing parameter set and instruct the processor to begin generating the personal audio stream by processing the digitized ambient audio in accordance with the new processing parameter set.

Claims

1. A personal audio system, comprising:

a housing configured to interface with a user'"'"'s ear;

an input subsystem disposed within the housing and comprising a microphone, a preamplifier, and an analog to digital converter coupled to one another, the input subsystem configured to convert ambient sound into digitized ambient audio;

a processor to generate a personal audio stream by processing the digitized ambient audio in accordance with an active processing parameter set, wherein the personal audio stream is a modified version of the digitized ambient audio;

an event detector to detect a trigger event other than manual selection by the user from a set of trigger events, wherein at least one of the trigger events includes a location of the personal audio system;

a controller configured to, in response to detection of the at least one of the trigger events;

transmit a most recent snippet of the digitized ambient audio and the location of the personal audio system to a knowledgebase remote from the personal audio system, wherein the most recent snippet of the ambient audio stream comprises a duration of the digitized ambient audio that occurs immediately preceding the trigger event; and

receive from the knowledgebase remote from the personal audio system a new processing parameter set associated with the location of the personal audio system and instruct the processor to begin generating the personal audio stream by processing the digitized ambient audio in accordance with the new processing parameter set, wherein the new processing parameter set is learned by the knowledgebase remote from the personal audio system based at least in part from one or more audio snippets and associated metadata uploaded to the knowledgebase remote from the personal audio system by a plurality of other personal audio systems; and

an output subsystem disposed within the housing and in communication with the processor, the output subsystem comprising a digital to analog converter, an amplifier and a speaker coupled to one another, the output subsystem configured to convert the digitized ambient audio into processed output sound for the user'"'"'s ear.

2. The personal audio system of claim 1, wherein at least one of the trigger events includes detecting, within the digitized ambient audio, an audio feature that is associated with the new processing parameter set.

3. The personal audio system of claim 1, wherein at least one of the trigger events includes detecting, within the digitized ambient audio, that an audio feature is not one that is associated with the active processing parameter set.

4. The personal audio system of claim 1 wherein the trigger event is detected in one of audio snippet data and audio snippet metadata based upon the digitized ambient audio.

5. The personal audio system of claim 1, further comprising:

a geo-locator to determine a current location of the personal audio system; and

wherein at least one of the trigger events is detecting, using the geo-locator, that the personal audio system has moved to the location that is associated with the new processing parameter set.

6. The personal audio system of claim 1, further comprising a parameter memory that stores one or more processing parameter sets including the active parameter set and the new processing parameter set.

7. The personal audio system of claim 1, wherein the controller is further configured to

receive, from the knowledgebase, one or more processing parameter sets derived by the knowledgebase from snippets and associated metadata received by the knowledgebase from a plurality of personal audio systems, and

store the one or more processing parameter sets received from the knowledgebase in a parameter memory.

8. The personal audio system of claim 1, wherein the processor is disposed within the housing.

9. The personal audio system of claim 1, wherein:

the housing is an earbud housing configured to fit, at least partially, within and be supported by the user'"'"'s ear.

10. A method for processing ambient sound in a personal audio system, comprising:

converting ambient sound into digitized ambient audio using an input subsystem disposed within a housing, the housing comprising a microphone, a preamplifier, and an analog to digital converter coupled to one another;

generating a personal audio stream by using a processor to process the digitized ambient audio in accordance with an active processing parameter set, wherein the personal audio stream is a modified version of the digitized ambient audio;

detecting, using an event trigger, a trigger event other than manual selection by a user of the personal audio system from a set of trigger events, wherein at least one of the trigger events includes a location of the personal audio system; and

in response to detection of the at least one of the trigger events, a controller;

transmitting a most recent snippet of the digitized ambient audio and the location of the personal audio system to a knowledgebase remote from the personal audio system, wherein the most recent snippet of the ambient audio stream comprises a duration of the digitized ambient audio that occurs immediately preceding the trigger event; and

receiving from the knowledgebase remote from the personal audio system a new processing parameter set associated with the location of the personal audio system and instructing the processor to begin generating the personal audio stream by processing the ambient audio stream in accordance with the new processing parameter set, wherein the new processing parameter set is learned by the knowledgebase remote from the personal audio system based at least in part from one or more audio snippets and associated metadata uploaded to the knowledgebase remote from the personal audio system by a plurality of other personal audio systems; and

converting the digitized ambient audio into processed output sound for the user'"'"'s ear using an output subsystem disposed within the housing and in communication with the processor, the output subsystem comprising a digital to analog converter, an amplifier and a speaker coupled to one another.

11. The method of claim 10, wherein at least one of the trigger events includes detecting, within the digitized ambient audio, an audio feature that is associated with the new processing parameter set.

12. The method of claim 10, wherein at least one of the trigger events includes detecting, within the digitized ambient audio, that an audio feature is not one that is associated with the active processing parameter set.

13. The method of claim 10 wherein at least one of the trigger events includes detecting in one of audio snippet data and audio snippet metadata based upon the digitized ambient audio.

14. The method of claim 10, further comprising:

determining a current location of the personal audio system using a geo-locator; and

wherein at least one of the trigger events includes detecting, using the geo-locator, that the personal audio system has moved to the location that is associated with the new processing parameter set.

15. The method of claim 10, further comprising storing one or more processing parameter sets in a parameter memory, the one or more processing parameter sets including the active parameter set and the new processing parameter set.

16. The method of claim 15, comprising

receiving, from the knowledgebase, one or more processing parameter sets derived by the knowledgebase from snippets and associated metadata received by the knowledgebase from a plurality of personal audio systems, and

storing the one or more processing parameter sets received from the knowledgebase in the parameter memory.

17. A system, comprising:

a knowledgebase; and

a personal audio system in communications with the knowledgebase via a network, the personal audio system comprising;

a processor to generate a personal audio stream by processing digitized ambient audio in accordance with an active processing parameter set, wherein the personal audio stream is a modified version of the digitized ambient audio;

an event detector to detect a trigger event other than manual selection by a user of the personal audio system from a set of trigger events, wherein at least one of the trigger events includes a location of the personal audio system; and

a controller configured to, in response to detection of the at least one of the trigger events;

transmit a most recent snippet of the digitized ambient audio and the location of the personal audio system to a knowledgebase remote from the personal audio system, wherein the most recent snippet of the ambient audio stream comprises a duration of the digitized ambient audio that occurs immediately preceding the trigger event; and

receive from the knowledgebase remote from the personal audio system a new processing parameter set associated with the location of the personal audio system and instruct the processor to begin generating the personal audio stream by processing the digitized ambient audio in accordance with the new processing parameter set, wherein the new processing parameter set is learned by the knowledgebase remote from the personal audio system based at least in part from one or more audio snippets and associated metadata uploaded to the knowledgebase remote from the personal audio system by a plurality of other personal audio systems.

18. The system of claim 17, wherein the knowledgebase is configured to transmit the new processing parameter set to the personal audio system when the trigger event is an audio feature detected by the knowledgebase within an ambient profile of the digitized ambient audio.

19. The system of claim 17, wherein the knowledgebase is configured to transmit the new processing parameter set to the personal audio system when the trigger event is that an audio feature is no longer detected by the knowledgebase within an ambient profile of the digitized ambient audio.

20. The system of claim 17, wherein the knowledgebase is configured to transmit the new processing parameter set to the personal audio system in response to a change in location of the personal audio system.