Personal audio system using processing parameters learned from user feedback

• US 9,736,264 B2
• Filed: 01/28/2016
• Issued: 08/15/2017
• Est. Priority Date: 04/08/2014
• Status: Active Grant

• Current Assignee: Dolby Laboratories Licensing Corporation (Dolby Laboratories Incorporated)
• Original Assignee: Doppler Labs, Inc.
• Inventors: Baker, Jeff, Wiggins, Daniel, Lanman, III, Richard Fritz, Kraft, Noah
• Primary Examiner(s): Zhang, Leshui
• Application Number:
  US15/008,704
• Publication Number:
  US 20160142820A1
• Time in Patent Office: 565 Days
• Field of Search: 381 72, 381 731, 381 74, 381 92, 381 26, 381 61, 381 63, 381 66, 381 714, 381 716, 381 718, 381 719, 381 7111, 381 7112, 381 98, 381 99, 381100, 381101, 381102, 381103, 4554141, 4554142, 4554042, 4554041, 455440, 4554221, 4554561, 4554562, 4554563, 4554564, 4554566, 455457, 700 94, 704E15047
• CPC Class Codes: G06F 3/165 Management of the audio stream, e.g. setting of volume, audio stream path
• CPC Class Codes: H04L 67/04 specially adapted for terminals or networks with limited capabilities; specially adapted for terminal portability
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• 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: H04L 69/04 Protocols for data compression, e.g. ROHC
• CPC Class Codes: H04L 69/18 Multiprotocol handlers, e.g. single devices capable of handling multiple protocols
• 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: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/50 Service provisioning or reconfiguring
• CPC Class Codes: H04W 4/80 Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication

Abstract

Learning personal audio systems and methods are disclosed. A learning personal audio system characterizes the digitized ambient sound so as to generate feature data for the digitized ambient sound, instructs a network interface to transmit the feature data to the remote server, requests one or more appropriate sound profiles from the remote server based upon the feature data, receives one or more selected sound profiles, selected by the remote server based upon the feature data, and initiates processing of the digitized ambient sound based upon the one or more selected sound profiles received from the remote server to generate digitized processed sound. The one or more selected sound profiles for the learning personal audio system are based upon sound profiles which are manually selected by a plurality of other users of personal audio systems similar to the learning personal audio system.

Claims

1. A 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, wherein the analog to digital converter is configured to convert ambient sound captured by the microphone and amplified by the preamplifier into digitized ambient sound;

a network interface configured to receive one or more processing parameter sets from a remote server;

a memory configured to store the one or more processing parameter sets received using the network interface, wherein a processing parameter set of the one or more processing parameter sets defines a type and degree of one or more processes to be performed on the digitized ambient sound;

a processor in communication with the input subsystem, the network interface, and the memory, the processor configured to;

extract feature data from the digitized ambient sound, wherein the feature data includes one or more numerical characterizations of the digitized ambient sound;

instruct the network interface to transmit the feature data and metadata to the remote server, wherein the metadata includes an identifier of the processing parameter set used to process the digitized ambient sound, wherein the remote server is configured to determine a consensus processing parameter set associated with the feature data and the metadata at least in part by;

grouping the feature data and the metadata received from the network interface with additional feature data and associated metadata received from other personal audio systems; and

determining the consensus processing parameter set for the group based upon processing parameters which are manually selected by a plurality of other users of the other personal audio systems;

request one or more appropriate processing parameter sets from the remote server;

receive one or more processing parameter sets, selected by the remote server based upon the feature data and the metadata, wherein the one or more processing parameter sets selected by the remote server includes the consensus processing parameter set; and

initiate processing of the digitized ambient sound based upon the one or more processing parameter sets selected and received from the remote server to generate digitized processed sound; 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, wherein the digital to analog converter is configured to convert the digitized processed sound into processed output sound outputted by the speaker for the user'"'"'s ear.

2. The system of claim 1 further comprising:

a geo-location engine in communication with the processor configured to determine a current location for the system,

wherein the metadata includes the current location and

the one or more processing parameter sets selected by the remote server are also based upon the current location of the system.

3. The system of claim 2 wherein the current location is used to select the one or more processing parameter sets selected by the remote server based upon the processing parameters which are manually selected by the plurality of other users of the other personal audio systems while the plurality of other users are near the current location.

4. The system of claim 2 wherein the one or more processing parameter sets selected by the remote server are selected based upon location type, as defined by a categorization made by the remote server comparing a location type of the current location to a database of potential location types, and based upon the processing parameters which are manually selected by the plurality of other users of the other personal audio systems while the plurality of other users are near the current location.

5. The system of claim 4 wherein the location type is one selected from the group comprising a stadium, a concert hall, a basketball court, an outdoor concert venue, a restaurant, an auditorium, an amphitheater, a classroom, a running trail, and an athletic field.

6. The system of claim 1 wherein the one or more processing parameter sets selected by the remote server are also selected using a context.

7. The system of claim 1 wherein the one or more processing parameter sets selected by the remote server are selected based upon a median one or more processing parameter sets selected by the plurality of other users.

8. The system of claim 1 wherein the one or more processing parameter sets selected by the remote server are selected based upon an average one or more processing parameter sets selected by the plurality of other users.

9. A method for processing personal audio based using forward feedback, comprising:

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

extracting feature data from the digitized ambient sound, wherein the feature data includes one or more numerical characterizations of the digitized ambient sound;

instructing a network interface to transmit the feature data and metadata to a remote server, wherein the metadata includes an identifier of a processing parameter set used to process the digitized ambient sound, wherein the processing parameter set defines a type and degree of one or more processes to be performed on the digitized ambient sound, wherein the remote server is configured to determine a consensus processing parameter set associated with the feature data and the metadata at least in part by;

grouping the feature data and the metadata received from the network interface with additional feature data and associated metadata received from other personal audio systems; and

determining the consensus processing parameter set for the group based upon processing parameters which are manually selected by a plurality of other users of the other personal audio systems;

requesting one or more appropriate processing parameter sets from the remote server;

receiving one or more selected processing parameter sets, selected by the remote server based upon the feature data and the metadata, wherein the one or more processing parameter sets selected by the remote server includes the consensus processing parameter set;

storing, in a memory, the one or more processing parameter sets selected by the remote server and received using the network interface;

initiating processing of the digitized ambient sound based upon the one or more selected processing parameter sets received from the remote server to generate digitized processed sound; and

converting the digitized processed sound into processed output sound for the user'"'"'s ear using an output subsystem disposed within the housing, the output subsystem comprising a digital to analog converter that converts the digitized processed sound into processed output sound, an amplifier that amplifies the processed output sound and a speaker that outputs the amplified processed output sound.

10. The method of claim 9 further comprising:

determining a current location using a geo-location engine;

wherein the metadata includes the current location; and

the one or more processing parameter sets selected by the remote server are also based upon the current location.

11. The method of claim 10 wherein the current location is used to select the one or more processing parameter sets selected by the remote server based upon the processing parameters which are manually selected by the plurality of other users of the other personal audio systems while the plurality of other users are near the current location.

12. The method of claim 10 wherein the one or more processing parameter sets selected by the remote server are selected based upon location type, as defined by a categorization made by the remote server comparing a location type of the current location to a database of potential location types, and based upon the processing parameters which are manually selected by the plurality of other users of the other personal audio systems while the plurality of other users are near the current location.

13. The method of claim 12 wherein the location type is one selected from the group comprising a stadium, a concert hall, a basketball court, an outdoor concert venue, a restaurant, an auditorium, an amphitheater, a classroom, a running trail, and an athletic field.

14. The method of claim 9 wherein the one or more processing parameter sets selected by the remote server are also selected using a context.

15. The method of claim 9 wherein the one or more processing parameter sets selected by the remote server are selected based upon a median one or more processing parameter sets selected by the plurality of other users.

16. The method of claim 9 wherein the one or more processing parameter sets selected by the remote server are selected based upon an average one or more processing parameter sets selected by the plurality of other users.

17. A non-transitory computer readable storage medium and comprising instructions, when executed by a processor, cause the processor to perform the steps of:

converting, by an analog to digital converter, ambient sound captured by a microphone and amplified by a preamplifier into digitized ambient sound using an input subsystem disposed within a housing, the input subsystem comprising the microphone, the preamplifier, and the analog to digital converter;

extracting feature data from the digitized ambient sound, wherein the feature data includes one or more numerical characterizations of the digitized ambient sound;

instructing a network interface to transmit the feature data and metadata to a remote server, wherein the metadata includes an identifier of the processing parameter set used to process the digitized ambient sound, wherein the processing parameter set defines a type and degree of one or more processes to be performed on the digitized ambient sound, wherein the remote server is configured to determine a consensus processing parameter set associated with the feature data and the metadata at least in part by;

grouping the feature data and the metadata received from the network interface with additional feature data and associated metadata received from other personal audio systems; and

determining the consensus processing parameter set for the group based upon processing parameters which are manually selected by a plurality of other users of the other personal audio systems;

requesting one or more appropriate processing parameter sets from the remote server;

receiving one or more processing parameter sets, selected by the remote server based upon the feature data and the metadata, wherein the one or more processing parameter sets selected by the remote server includes the consensus processing parameter set;

storing, in a memory, the one or more processing parameter sets selected by the remote server and received using the network interface;

initiating processing of the digitized ambient sound based upon the one or more selected processing parameter sets received from the remote server to generate digitized processed sound; and

converting the digitized processed sound into processed output sound for the user'"'"'s ear using an output subsystem disposed within the housing, the output subsystem comprising a digital to analog converter that converts the digitized processed sound into processed output sound, an amplifier that amplifies the processed output sound and a speaker that outputs the amplified processed output sound.

18. The tangible non-transitory computer readable storage medium of claim 17, further comprising instructions for determining a current location for the housing using a geo-location engine, wherein the metadata includes the current location, and wherein the one or more selected processing parameter sets are also based on the current location of the housing.