Adaptive filtering with machine learning
First Claim
Patent Images
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 Assignments
0 Petitions
Accused Products
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.
-
Citations
20 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. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
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. - View Dependent Claims (11, 12, 13, 14, 15, 16)
-
-
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. - View Dependent Claims (18, 19, 20)
-
Specification