Hearing aids for cognitive assistance using speaker recognition

Abstract

Implementations relate generally to hearing aids. In some implementations, a method includes receiving a sound at a hearing aid. The method further includes detecting a voice from the sound. The method further includes identifying the voice. The method further includes providing identity information associated with the voice.

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of U.S. Patent Application Serial No. 17 / 693,145, filed March 11, 2022, entitled "HEARING AID FOR COGNITIVE HELP USING SPEAKER RECOGNITION" (Attorney Docket No. 020699-119700US / Client Reference No. SYP346748US01), which is incorporated by reference in its entirety for all purposes as if set forth herein.

[0002] This application is related to U.S. patent application Ser. No. 17 / 693,139, entitled "HEARING AID FOR ALARMS AND OTHER SOUNDS," filed on March 11, 2022 (Attorney Docket No. 020699-119500US / Client Reference No. SYP346746US01), and U.S. patent application Ser. No. 17 / 693,142, entitled "HEARING AID IN-EAR ANNOUNCEMENTS," filed on March 11, 2022 (Attorney Docket No. 020699-119600US / Client Reference No. SYP346747US01), which are incorporated by reference in their entireties for all purposes as if set forth in this application. [Background technology]

[0003] Some people deal with age-related hearing loss. Hearing aids can help them by capturing, processing, and amplifying the sounds that pass through the user's ear canal. Some hearing aids are miniaturized to a point where they sit directly within the user's ear canal and are nearly invisible to others. The hearing aid picks up the sounds and amplifies them to a level that the user can hear. Summary of the Invention [Means for solving the problem]

[0004] Implementations relate generally to hearing aids. In some implementations, a system includes one or more processors and logic encoded in one or more non-transitory computer-readable storage media for execution by the one or more processors. The logic, when executed, is operable to cause the one or more processors to perform operations including determining characterization information from a voice, matching the characterization information from the voice to characterization information in a database, and identifying the person based on the matching.

[0005] With further regard to the system, in some implementations, the logic, when executed, is further operable to cause the one or more processors to perform operations including determining characterization information from the voice, matching the characterization information from the voice with characterization information in a database, and identifying the person based on the matching. In some implementations, the logic, when executed, is further operable to cause the one or more processors to perform operations including detecting multiple voices from the sound, identifying a dominant voice from the multiple voices, and providing identity information associated with the dominant voice. In some implementations, the logic, when executed, is further operable to cause the one or more processors to perform operations including generating a notification including identity information that identifies the person associated with the voice, and providing the identity information in the notification. In some implementations, the identity information is provided in an in-ear notification, the in-ear notification being audible to a user of the hearing aid. In some implementations, the logic, when executed, is further operable to cause the one or more processors to perform operations including establishing communication between the hearing aid and the mobile device, accessing the Internet via the mobile device, and the hearing aid sending and receiving data from the Internet via the mobile device. In some implementations, the logic, when executed, is further operable to cause the one or more processors to perform operations including identifying one or more voices from the sound in real time based on artificial intelligence.

[0006] Some implementations provide a non-transitory computer-readable storage medium having stored thereon program instructions that, when executed by one or more processors, are operable to cause the one or more processors to perform operations including determining characterization information from the voice, matching the characterization information from the voice with characterization information in a database, and identifying the person based on the matching.

[0007] Further with respect to the computer-readable storage medium, in some implementations, the instructions, when executed, are further operable to cause the one or more processors to perform operations including determining characterization information from the voice, matching the characterization information from the voice with characterization information in a database, and identifying the person based on the matching. In some implementations, the instructions, when executed, are further operable to cause the one or more processors to perform operations including detecting multiple voices from the sound, identifying a dominant voice from the multiple voices, and providing identity information associated with the dominant voice. In some implementations, the instructions, when executed, are further operable to cause the one or more processors to perform operations including generating a notification including identity information that identifies the person associated with the voice, and providing the identity information in the notification. In some implementations, the identity information is provided in an in-ear notification, the in-ear notification being audible to a user of the hearing aid. In some implementations, the instructions, when executed, are further operable to cause the one or more processors to perform operations including establishing communication between the hearing aid and the mobile device, accessing the Internet via the mobile device, and the hearing aid transmitting data to and receiving data from the Internet via the mobile device. In some implementations, the instructions, when executed, are further operable to cause the one or more processors to perform operations including identifying one or more voices from the sound in real time based on artificial intelligence.

[0008] In some implementations, the method includes determining characterization information from the voice, matching the characterization information from the voice with characterization information in a database, and identifying the person based on the matching.

[0009] Further with respect to the method, in some implementations the method further includes determining characterization information from the voice, matching the characterization information from the voice with the characterization information in the database, and identifying the person based on the matching. In some implementations the method further includes detecting a plurality of voices from the sound, identifying a dominant voice from the plurality of voices, and providing identity information associated with the dominant voice. In some implementations the method further includes generating a notification including identity information identifying a person associated with the voice, and providing the identity information in the notification. In some implementations the identity information is provided in an in-ear notification, the in-ear notification being audible to a user of the hearing aid. In some implementations the method further includes establishing communication between the hearing aid and a mobile device, accessing the Internet via the mobile device, and the hearing aid sending and receiving data to and from the Internet via the mobile device.

[0010] A further understanding of the nature and advantages of particular implementations disclosed herein may be realized by reference to the remaining portions of the specification and the attached drawings. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a block diagram of an example hearing aid and environment for providing cognitive assistance using speaker recognition that can be used in the implementations described herein. [Figure 2A] 1 is an image of an example hearing aid that can be used in the implementations described herein. [Figure 2B] 1 is an image of a hearing aid worn on the ear according to some implementations. [Figure 3A] 1 is an image of an example hearing aid that can be used in the implementations described herein. [Figure 3B] 1 is an image of a hearing aid placed in an ear canal, according to some embodiments. [Figure 4] 1 is an example flow diagram for providing cognitive assistance using hearing aids and speaker recognition, according to some embodiments. [Diagram 5]FIG. 1 is a block diagram of an example network environment that can be used with the implementations described herein. [Figure 6] FIG. 1 is a block diagram of an example computer system that can be used to implement the methods described herein. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Implementations relate generally to hearing aids, and more particularly to hearing aids that use speaker recognition to provide cognitive assistance. As described in further detail herein, in various implementations, a system receives a sound at a hearing aid. The system further detects a voice from the sound. The system further identifies the voice. The system further provides identity information associated with the voice.

[0013] Implementations allow users to receive such identity information in real time when talking to other people at home or elsewhere (e.g., on the street). In various implementations, the system can automatically provide identity information of the person who is talking to the hearing aid wearer. In some scenarios where the hearing aid is worn over the ear, the user / hearing aid wearer can tap the hearing aid several times to start the identity process or to start the announcement of the identity of the person who is speaking. In other scenarios, the wearer can speak commands such as "identity" or "identify" to the hearing aid. If the wearer is using a smart device for control, the wearer can obtain identity information using a user interface on the smart device that can be announced through the hearing aid. In various implementations, the system provides in-ear notifications containing the identity information so that the hearing aid user can hear the identity information but other people nearby cannot hear the identity information. This unobtrusively notifies the user without disturbing other people or interrupting the conversation between the user and other people.

[0014] 1 is a block diagram of an example hearing aid 100 and environment for providing cognitive assistance using speaker recognition that can be used in the implementations described herein. As shown, the environment includes a hearing aid 100 that includes a system 102, a microphone 104, and a speaker 106.

[0015] In various implementations, the system 102 of the hearing aid 100 can communicate with the Internet directly or via a mobile device such as a smartphone, computer, etc. The hearing aid 100 can be enabled for tethering to a mobile device that connects to the Internet or other network, thereby continuously streaming audio to the Internet for analysis by a web server. The system 102 can communicate with the Internet via any suitable communication network, such as a Bluetooth network, a Wi-Fi network, etc., or with another device, such as a mobile device.

[0016] As described in further detail herein, the system 102 of the hearing aid 100 receives external sounds including various types of sounds from the surrounding environment. In general, the hearing aid 100 may amplify and / or attenuate the detected sounds according to implementations described herein. The detected sounds may include various types of sounds from the surrounding environment including voices from persons or people near the user wearing the hearing aid 100. In various implementations, the system 102 provides identity information associated with each of one or more detected voices.

[0017] In some implementations, the system 102 attenuates the detected sounds so that any identity information provided by the system 102 can be better heard by a user wearing the hearing aid 100. Further implementations for the operation of the hearing aid 100 are described in further detail herein, for example in relation to FIG.

[0018] For ease of explanation, Figure 1 shows one block each for the system 102, microphone 104, and speaker 106. Blocks 102, 104, and 106 may represent multiple systems, microphones, and speakers depending on the particular implementation. In other implementations, the hearing aid 100 may not have all the components shown, and / or may have other elements, including other types of elements instead of or in addition to the components shown.

[0019] Although the implementations described herein may be performed by system 102, in other implementations, any suitable component or combination of components associated with system 102, or any suitable processor or processors associated with system 102, may facilitate execution of the implementations described herein.

[0020] Figure 2A is an image of an example hearing aid 200 that can be used in the implementations described herein. Figure 2B is an image of the hearing aid 200 worn over the ear 202, according to some implementations. As shown, the hearing aid 200 is worn on the outside of the ear 202 and wraps around the top of the ear 202. In various implementations, the receiver of the hearing aid is inserted into the ear canal.

[0021] FIG 3A is an image of an example hearing aid 300 that can be used in the implementations described herein. FIG 3B is an image of a hearing aid 300 placed in the ear canal of an ear 302, according to some implementations. As shown, the hearing aid 300 inserted in the ear canal of the ear 302 is difficult to see. The hearing aids shown in FIGS 2A, 2B, 3A and 3B are example implementations of hearing aid hardware. The specific type of hearing aid hardware can vary depending on the implementation.

[0022] 4 is an example flow diagram of providing cognitive assistance using hearing aids and speaker recognition according to some implementations. With reference to both FIG. 1 and FIG. 2, the method begins at block 402 where a system, such as system 102, receives sound at a hearing aid.

[0023] The system detects a voice from the sounds in block 404. For example, the system can detect various types of sounds such as traffic sounds, dogs barking, voices, etc.

[0024] At block 406, the system identifies the voice. In various implementations, to identify the voice, the system determines characterization information from the voice. The characterization information may include various qualities of the voice, including timbre, pitch, volume, etc. The specific qualities may vary depending on the implementation. The system may collect the characterization information using any suitable characterization technique. The system then matches the characterization information from the voice with characterization information in a database. The system then identifies the person based on the match.

[0025] In one example scenario, the system may identify the voice as the user's daughter or other known person (other family member, friend, etc.). A system that provides identity information to a user may assist the user in scenarios where the user has cognitive issues that challenge short-term memory (e.g., cognitive issues related to aging, accidents, etc.). In some implementations, the hearing aid may also receive information (e.g., caller ID) from a mobile device such as a smartphone to help populate voice recognition for useful phone contacts.

[0026] A system that provides identity information to a user also avoids scenarios where a stranger or imposter claims to be a different person. In such an imposter scenario, the user may hear the daughter's name (e.g., "It's Kate"), but the system does not recognize a voice that matches the daughter's. In some implementations, the system can indicate to the user that the name does not match, so the user can take action accordingly.

[0027] In various implementations, the system identifies one or more voices from the sound in real time based on artificial intelligence and machine learning. The system may also previously identify one or more voices from the sound based on artificial intelligence and machine learning. For example, a user may ask a given speaker to speak a series of words to the system (e.g., read a text or isolated vocabulary, etc.). The system may be pre-trained prior to a conversation, or may analyze a given voice in real time during a conversation to recognize a particular voice or fine-tune the voice recognition to improve accuracy.

[0028] In block 408, the system provides identity information associated with the voice. In the above scenario, the system provides identity information associated with the voice after identifying the voice (e.g., the daughter's voice). In various implementations, the system provides the identity information in an in-ear notification, which is then audible to the hearing aid user but not to other persons. Thus, the user can discreetly learn the person associated with the voice.

[0029] The system may detect multiple voices from the sound. This scenario may be a scenario where there are multiple conversations with or without user involvement. In some implementations, the system may identify a primary voice from the multiple voices. In some implementations, the system may determine the primary voice based on various factors. Such factors may include voice volume, voice location, etc. For example, the primary voice may be the loudest voice. In another example, the primary voice may be a voice from in front of the user. The system may determine that a voice is in front of the user based on two hearing aids detecting similar voice volumes when another person is standing directly in front of the user. In some implementations, the direction of the hearing aid microphone may also determine whether the voice originates in front of or behind the user. After identifying the primary voice, the system may recognize the voice based on suitable voice recognition technology and then provide the user with identity information related to the primary voice.

[0030] In various implementations, the system generates a notification that includes identity information that identifies the person associated with the voice. In some implementations, the notification can also include other information in addition to the identity information. For example, in some implementations, the system can provide biographical information. This is useful if the user knows the speaker and the system indicates in the notification how the user knows the speaker, the speaker's title, the speaker's primary family, etc. The system provides the identity information and any other relevant information associated with the other person in the notification.

[0031] In various implementations, the system provides the identity information during a moment based on one or more predefined announcement policies. For example, in some implementations, the predefined announcement policy is to deliver the identity information immediately upon recognizing a person associated with the voice. In some implementations, the predefined announcement policy is to deliver the identity information at a delayed time (e.g., during a pause in a conversation). For example, the system may provide the identity information upon detecting silence, such as a pause in a conversation between a user and another person. This allows the system to avoid interfering with the conversation.

[0032] In some implementations, the system may attenuate or filter certain sounds that are deemed unimportant for the user to hear. For example, the system may attenuate background noises such as wind, traffic, etc. This allows the user to easily distinguish between important sounds (such as alarms, notifications, announcements, etc.) and unimportant sounds (such as wind, traffic, etc.). The system may utilize any suitable frequency attenuation or noise canceling technique.

[0033] In some implementations where a user wears hearing aids in both ears, the system may deliver alarms, notifications, announcements, etc. to the user in one hearing aid but not the other, allowing the system to deliver different types of information simultaneously. In such a scenario, the system may increase the volume of alarms, notifications, and announcements above other ambient sounds.

[0034] As mentioned above, the system establishes communication between the hearing aid and the mobile device, and can also access the Internet via the mobile device. Thus, the system allows the hearing aid to send and receive data to and from the Internet via the mobile device. This is beneficial in that the hearing aid can utilize the power and other resources of the mobile device.

[0035] Although steps, operations, or computations may be shown in a particular order, the order may be changed in a particular implementation. Other orders of steps are possible, depending on the particular implementation. In some particular implementations, multiple steps shown in this specification as sequential may be performed simultaneously. Also, some implementations may not have all steps and / or may have other steps instead of or in addition to those shown in this specification.

[0036] The implementations described herein provide various advantages, for example, they provide cognitive assistance using speaker recognition, they also identify voices and provide identity information associated with such voices.

[0037] 5 is a block diagram of an example network environment 500 that may be used in some implementations described herein. In some implementations, the network environment 500 includes a system 502 that includes a server device 504 and a database 506. For example, the system 502 may be used to implement a system of mobile devices in communication with the hearing aids described herein and to perform the implementations described herein.

[0038] The network environment 500 also includes client devices 510 and 520, which may represent two hearing aids worn by the user U1. For example, one client device may represent a hearing aid for the right ear and the other client device may represent a hearing aid for the left ear. The client devices 510 and 520 may communicate with the system 502 and / or with each other directly or via the system 502. The network environment 500 also includes a network 550 that allows the system 502 and the client devices 510 and 520 to communicate. The network 550 may be any suitable communication network, such as a Wi-Fi network, a Bluetooth network, the Internet, etc.

[0039] Although system 502 is shown separate from client devices 510 and 520, variations of system 502 may be integrated into client device 510 and / or client device 520, allowing each of client devices 510 and 520 to communicate directly with the Internet or another network.

[0040] For ease of explanation, Figure 5 shows one block each of system 502, server device 504, and network database 506. Blocks 502, 504, and 506 may represent multiple systems, server devices, and network databases. Also, there may be any number of client devices. In other implementations, environment 500 may have less than all of the components shown and / or may have other elements, including other types of elements instead of or in addition to the components shown.

[0041] The implementations described herein may be performed by server device 504 of system 502, although in other implementations, any suitable component or combination of components associated with system 502, or any suitable processor or processors associated with system 502, may facilitate execution of the implementations described herein.

[0042] FIG. 6 is a block diagram of an example computer system 600 that can be used in some implementations described herein. For example, computer system 600 can be used to implement server device 504 of FIG. 5 and / or system 102 of FIG. 1 as well as to execute implementations described herein. In some implementations, computer system 600 can include a processor 602, an operating system 604, memory 606, and an input / output (I / O) interface 608. In various implementations, processor 602 can be used to implement various functions and features described herein as well as to execute implementations of methods described herein. Although the implementations described herein are described as being executed by processor 602, any suitable component or combination of components of computer system 600, or any suitable processor or processors associated with computer system 600 or any suitable system, can also execute the steps described. The implementations described herein can be executed on a user device, a server, or a combination of both.

[0043] Computer system 600 also includes software applications 610, which may be stored in memory 606 or any other suitable storage location or computer readable medium. The software applications 610 provide instructions that enable processor 602 to perform the implementations and other functions described herein. The software applications 610 may also include engines, such as a network engine, that perform various functions related to one or more networks and network communications. The components of computer system 600 may be implemented by one or more processors, or any combination of hardware devices, any combination of hardware, software, firmware, and the like.

[0044] 6 illustrates one block each of processor 602, operating system 604, memory 606, I / O interfaces 608, and software applications 610. These blocks 602, 604, 606, 608, and 610 may represent multiple processors, operating systems, memories, I / O interfaces, and software applications. In various implementations, computer system 600 may have less than all of the components illustrated and / or may have other elements including other types of components instead of or in addition to the components illustrated.

[0045] Although described with respect to specific implementations, these specific implementations are illustrative only and not limiting, and the concepts illustrated in these embodiments may be applied to other embodiments and implementations.

[0046] In various implementations, software for execution by one or more processors is encoded on one or more non-transitory computer-readable media that, when executed by the one or more processors, performs the implementations and other functions described herein.

[0047] The routines of a particular implementation may be implemented using any suitable programming language, including C, C++, C#, Java, JavaScript, assembly language, etc. Different programming techniques may be used, such as procedural or object-oriented. The routines may be executed on a single processing unit or multiple processors. Although steps, operations, or computations may be shown in a particular order, this order may be changed in different particular implementations. In some particular implementations, multiple steps shown herein as sequential may be executed simultaneously.

[0048] Certain implementations may be implemented in a non-transitory computer-readable storage medium (also referred to as a machine-readable storage medium) used by or connected to an instruction execution system, apparatus, or device. Certain implementations may also be implemented in the form of control logic in software or hardware, or a combination thereof. The control logic, when executed by one or more processors, may perform the implementations and other functions described herein. For example, tangible media, such as hardware storage devices, may be used to store the control logic, which may include executable instructions.

[0049] Particular implementations may be implemented using programmable general-purpose digital computers, and / or using application specific integrated circuits, programmable logic devices, field programmable gate arrays, optical, chemical, biological, quantum or nano-engineered systems, components and mechanisms. In general, the functionality of a particular implementation may be realized by any means known in the art. Distributed networked systems, components and / or circuits may also be used. Communication or transfer of data may be by wire, wireless or any other means.

[0050] A "processor" may include any suitable hardware and / or software system, mechanism, or component that processes data, signals, or other information. A processor may include a system having a general-purpose central processing unit, multiple processing units, dedicated circuitry, or other systems for implementing functions. Processing need not be limited to a geographic location or have time limitations. For example, a processor may perform its functions in "real-time," "offline," "batch mode," etc. Portions of the processing may also be performed at different times and in different locations by different (or the same) processing systems. A computer may be any processor in communication with a memory. Memory may be any suitable data storage, memory, and / or non-transitory computer-readable storage medium, including electronic storage such as random access memory (RAM), read-only memory (ROM), magnetic storage (such as a hard disk drive), flash, optical storage (such as a CD or DVD), magnetic or optical disk, or other tangible medium suitable for storing instructions (e.g., program or software instructions) to be executed by a processor. For example, tangible media such as hardware storage may be used for storage of control logic, which may include executable instructions. The instructions may also be provided in or as electrical signals, such as in a form of software as a service (SaaS) delivered from a server (eg, a distributed system and / or a cloud computing system).

[0051] It will also be understood that one or more of the elements shown in the drawings / figures may be implemented in a more separate or integrated manner, or removed or inoperative in some cases, when useful according to a particular application.It is also within the spirit and scope of the present invention to implement a program or code that may be stored on a machine-readable medium that enables a computer to perform any of the methods described above.

[0052] As used throughout this specification and the claims that follow, the terms "a" and "the" include plural references unless the context clearly indicates otherwise. Additionally, as used throughout this specification and the claims that follow, the meaning of "in" includes the meanings "in" and "on," unless the context clearly indicates otherwise.

[0053] Although specific implementations have been described herein, it will be understood that the disclosure above is open to modification, various changes and substitutions, and that in some instances, some features of a specific implementation may be used without the corresponding use of other features without departing from the scope and spirit of the described implementation. Accordingly, many modifications may be made to adapt a particular situation or material to the basic scope and spirit. [Explanation of symbols]

[0054] 100 Hearing aids 102 System 104 Mike 106 Speaker

Claims

1. one or more processors; logic for execution by the one or more processors, encoded in one or more non-transitory computer-readable storage media; the logic, when executed, Receiving sound at a hearing aid; detecting a voice from the sound; identifying said voice; providing identity information associated with said voice; and operable to cause the one or more processors to perform operations including A system characterized by:

2. The logic, when executed, determining characterization information from the voice; and matching characterization information from the voice with characterization information in a database; identifying the person based on the matching; and The system of claim 1 , further operable to cause the one or more processors to perform operations including:

3. The logic, when executed, detecting a plurality of voices from the sound; identifying a dominant voice from the plurality of voices; providing identity information associated with said dominant voice; The system of claim 1 , further operable to cause the one or more processors to perform operations including:

4. The logic, when executed, generating a notification including the identity information identifying a person associated with the voice; providing said identity information in said notification; The system of claim 1 , further operable to cause the one or more processors to perform operations including:

5. said identity information being provided in an in-ear notification, said in-ear notification being audible to a user of said hearing aid; The system of claim 1 .

6. The logic, when executed, establishing communication between the hearing aid and a mobile device; accessing the Internet via said mobile device and said hearing aid transmitting and receiving data to and from said Internet via said mobile device; The system of claim 1 , further operable to cause the one or more processors to perform operations including:

7. the logic, when executed, is further operable to cause the one or more processors to perform operations including identifying one or more voices from the sound in real time based on artificial intelligence. The system of claim 1 .

8. A non-transitory computer-readable storage medium having stored thereon program instructions that, when executed by one or more processors, Receiving sound at a hearing aid; detecting a voice from the sound; identifying said voice; providing identity information associated with said voice; and operable to cause the one or more processors to perform operations including A computer-readable storage medium comprising:

9. The program instructions, when executed, determining characterization information from the voice; and matching characterization information from the voice with characterization information in a database; identifying the person based on the matching; and 9. The computer-readable storage medium of claim 8, further operable to cause the one or more processors to perform operations including:

10. The program instructions, when executed, detecting a plurality of voices from the sound; identifying a dominant voice from the plurality of voices; providing identity information associated with said dominant voice; 9. The computer-readable storage medium of claim 8, further operable to cause the one or more processors to perform operations including:

11. The program instructions, when executed, generating a notification including the identity information identifying a person associated with the voice; providing said identity information in said notification; 9. The computer-readable storage medium of claim 8, further operable to cause the one or more processors to perform operations including:

12. said identity information being provided in an in-ear notification, said in-ear notification being audible to a user of said hearing aid; The computer-readable storage medium of claim 8.

13. The program instructions, when executed, establishing communication between the hearing aid and a mobile device; accessing the Internet via said mobile device and said hearing aid transmitting and receiving data to and from said Internet via said mobile device; 9. The computer-readable storage medium of claim 8, further operable to cause the one or more processors to perform operations including:

14. The program instructions, when executed, are further operable to cause the one or more processors to perform operations including identifying one or more voices from the sound in real time based on artificial intelligence. The computer-readable storage medium of claim 8.

15. 1. A computer-implemented method, comprising: Receiving sound at a hearing aid; detecting a voice from the sound; identifying said voice; providing identity information associated with said voice; The method according to claim 1, further comprising:

16. determining characterization information from the voice; and matching characterization information from the voice with characterization information in a database; identifying the person based on the matching; and The method of claim 15 further comprising:

17. detecting a plurality of voices from the sound; identifying a dominant voice from the plurality of voices; providing identity information associated with said dominant voice; The method of claim 15 further comprising:

18. generating a notification including the identity information identifying a person associated with the voice; providing said identity information in said notification; The method of claim 15 further comprising:

19. said identity information being provided in an in-ear notification, said in-ear notification being audible to a user of said hearing aid; The method of claim 15.

20. establishing communication between the hearing aid and a mobile device; accessing the Internet via said mobile device and said hearing aid transmitting and receiving data to and from said Internet via said mobile device; The method of claim 15 further comprising:

Images