Audio signal processing method, hearing aid and computer-readable storage medium

Abstract

The present invention discloses an audio signal processing method, a hearing aid and a computer-readable storage medium. The method includes: when receiving audio signals corresponding to multiple signal sources, determining the priority levels corresponding to each of the signal sources; determining a target signal source based on the priority levels; amplifying the target audio signal corresponding to the target signal source; and driving a bone oscillator of the hearing aid according to the amplified target audio signal. The present invention aims to improve the switching efficiency of the signal sources of the hearing aid, achieve the purpose of automatically switching the hearing aid between a hearing mode and a Bluetooth mode, and facilitate the use by the user.

Description

Technical Field

[0001] The present invention relates to the technical field of hearing aids, and in particular to an audio signal processing method, a hearing aid, and a computer-readable storage medium. Background Art

[0002] With the development of communication technology and increasing social care for hearing-impaired people, many hearing aids are equipped with a Bluetooth mode. In the hearing aid mode, the hearing aid collects various sounds around the user through a pickup microphone. Then, through an amplifier, the useful signals collected by the pickup microphone are amplified and then played. In the Bluetooth mode, the hearing aid can receive audio signals transmitted by other devices through Bluetooth, and play them after amplification processing. Since the hearing aid is provided with a hearing aid mode and a Bluetooth mode, the types of audio signals that need to be amplified are rich. However, the sounds played after processing various types of audio signals become noisy and chaotic. Especially for hearing-impaired people, their need for pure and clean sounds is greater, otherwise it is not conducive to hearing aid.

[0003] In the related art, for the switching of various types of audio signals, such as audio signals transmitted by Bluetooth or audio signals collected by a pickup microphone, it is necessary to manually switch and set the signal source, resulting in too low efficiency of signal source switching.

[0004] The above content is only used to assist in understanding the technical solution of the present invention, and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main object of the present invention is an audio signal processing method, a hearing aid, and a computer-readable storage medium, aiming to achieve the effect of improving the switching efficiency of the signal source of the hearing aid.

[0006] To achieve the above object, the present invention provides an audio signal processing method applied to a hearing aid, and the method includes:

[0007] When receiving audio signals corresponding to multiple signal sources, determining the priority levels corresponding to each of the signal sources;

[0008] Based on the priority levels, determining a target signal source;

[0009] Amplifying the target audio signal corresponding to the target signal source;

[0010] Driving a bone oscillator of the hearing aid according to the amplified target audio signal.

[0011] Optionally, the target signal source is an interactive device that establishes a Bluetooth connection with the hearing aid. After the step of determining the target signal source based on the priority levels, the method further includes:

[0012] When receiving the voice collection instruction sent by the interaction device, collect voice data through the microphone of the hearing aid;

[0013] Send the voice data to the interaction device.

[0014] Optionally, the target signal source is the call module of the interaction device. After the step of collecting voice data through the microphone of the hearing aid, the following steps are further included:

[0015] Identify the human voice data in the voice data according to the voice data;

[0016] Judge whether there is a conversation request including personnel other than the user bound to the hearing aid in the human voice data;

[0017] When there is the conversation request, output an occupation prompt of the bone oscillator and / or output a conversation request prompt.

[0018] Optionally, the step of outputting the conversation request prompt includes:

[0019] Determine the audio signal corresponding to the conversation request according to the voice data;

[0020] When receiving the stop voice collection instruction sent by the interaction device, amplify the audio signal corresponding to the conversation request;

[0021] Drive the bone oscillator of the hearing aid according to the amplified audio signal corresponding to the conversation request.

[0022] Optionally, the target signal source is the audio and video module of the interaction device. After the step of driving the bone oscillator of the hearing aid according to the amplified target audio signal, the following steps are further included:

[0023] Collect voice data through the microphone of the hearing aid;

[0024] Identify whether the voice data is the human voice data of the user bound to the hearing aid;

[0025] When it is recognized that the voice data is the human voice data of the bound user, use the microphone as the target signal source, and re-execute the step of amplifying the target audio signal corresponding to the target signal source.

[0026] Optionally, after the step of driving the bone oscillator of the hearing aid according to the amplified target audio signal, the following steps are further included:

[0027] Collect voice data through the microphone of the hearing aid;

[0028] Determine a switching instruction according to the voice data;

[0029] Change the target signal source according to the switching instruction, and re-execute the step of amplifying the target audio signal corresponding to the target signal source.

[0030] Optionally, before the step of determining the switching instruction according to the voice data, the method further includes:

[0031] Obtain the historical voice data of the user bound to the hearing aid;

[0032] Construct a voice recognition model associated with the bound user according to the historical voice data;

[0033] The step of determining the switching instruction according to the voice data includes:

[0034] Input the voice data into the voice recognition model to determine the switching instruction.

[0035] Optionally, after the step of driving the bone oscillator of the hearing aid according to the amplified target audio signal, the method further includes:

[0036] Collect voice data through the pickup microphone of the hearing aid;

[0037] Identify whether there is key attention information in the voice data, where the key attention information includes identification words and danger warning information;

[0038] When the key attention information is recognized, amplify the audio signal corresponding to the key attention information as a new target audio signal, and re-execute the step of driving the bone oscillator of the hearing aid according to the amplified target audio signal.

[0039] In addition, to achieve the above object, the present invention further provides a hearing aid, which includes a memory, a processor, and an audio signal processing program stored on the memory and executable on the processor. When the audio signal processing program is executed by the processor, it implements the steps of the audio signal processing method as described above.

[0040] In addition, to achieve the above object, the present invention further provides a computer-readable storage medium, on which an audio signal processing program is stored. When the audio signal processing program is executed by a processor, it implements the steps of the audio signal processing method as described above.

[0041] An audio signal processing method, a hearing aid, and a computer-readable storage medium proposed in an embodiment of the present invention, when receiving audio signals corresponding to multiple signal sources, determine the priority corresponding to each of the signal sources; determine a target signal source based on the priority; perform amplification processing on the target audio signal corresponding to the target signal source; drive the bone oscillator of the hearing aid according to the amplified target audio signal. By dividing the priority of the signal sources that the hearing aid will receive, when receiving multiple audio signals, the target audio signal of the target signal source can be preferentially processed according to the priority of the signal source. In this way, the current signal source of the hearing aid can be automatically switched to a target signal source with a higher priority and more in line with the user's needs, so the switching efficiency of the hearing aid signal source can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a schematic diagram of the terminal structure of the hardware operating environment related to the solution of the embodiment of the present invention;

[0043] Figure 2 It is a schematic flowchart of an embodiment of the audio signal processing method of the present invention;

[0044] Figure 3 It is a schematic flowchart of another embodiment of the audio signal processing method of the present invention.

[0045] The realization, functional features, and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0047] In the related art, in order to make the played sound clearer, the hearing aid will reduce the played audio signal as much as possible, so it is necessary to switch the signal source of the played audio signal. Currently, it is necessary to manually switch the signal source, resulting in too low switching efficiency of the hearing aid signal source.

[0048] In order to improve the switching efficiency of the hearing aid signal source, an embodiment of the present invention proposes an audio signal processing method, a hearing aid, and a computer-readable storage medium. The main steps of the method include:

[0049] When receiving audio signals corresponding to multiple signal sources, determine the priority corresponding to each of the signal sources;

[0050] Determine a target signal source based on the priority;

[0051] Perform amplification processing on the target audio signal corresponding to the target signal source;

[0052] Drive the bone oscillator of the hearing aid according to the amplified target audio signal.

[0053] In this way, by dividing the priority of the signal sources received by the hearing aid, when multiple audio signals are received, the target audio signal of the target signal source is preferentially processed. Automatically switch the current signal source of the hearing aid to the target signal source with a higher priority and more in line with the user's needs. Therefore, the switching efficiency of the hearing aid signal source can be improved.

[0054] The following will describe in detail the content protected by the claims of the present invention with reference to the accompanying drawings.

[0055] As Figure 1 shown, Figure 1 is a schematic diagram of the terminal structure of the hardware operating environment involved in the embodiment solution of the present invention.

[0056] The terminal in the embodiment of the present invention can be a hearing aid.

[0057] As Figure shown, the terminal may include: a processor 1001, such as a CPU, a memory 1003, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The memory 1003 can be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. Optionally, the memory 1003 can also be a storage device independent of the aforementioned processor 1001.

[0058] Those skilled in the art can understand that ​ the terminal structure shown in

[0059] does not constitute a limitation on the terminal, and may include more or fewer components than shown in the figure, or combine some components, or arrange different components. ​ shown, the memory 1003, as a computer storage medium, may include an operating system and an audio signal processing program.

[0060] In ​ the terminal shown, the processor 1001 can be used to call the audio signal processing program stored in the memory 1003 and perform the following operations:

[0061] When receiving audio signals corresponding to multiple signal sources, determine the priority corresponding to each of the signal sources;

[0062] Based on the priority, determine the target signal source;

[0063] Amplify the target audio signal corresponding to the target signal source;

[0064] Drive the bone oscillator of the hearing aid according to the amplified target audio signal.

[0065] Further, the processor 1001 may call the audio signal processing program stored in the memory 1003 and further perform the following operations:

[0066] When receiving the voice collection instruction sent by the interaction device, collect voice data through the voice pickup microphone of the hearing aid;

[0067] Send the voice data to the interaction device.

[0068] Further, the processor 1001 may call the audio signal processing program stored in the memory 1003 and further perform the following operations:

[0069] When receiving the voice collection instruction sent by the interaction device, collect voice data through the voice pickup microphone of the hearing aid;

[0070] Send the voice data to the interaction device.

[0071] Further, the processor 1001 may call the audio signal processing program stored in the memory 1003 and further perform the following operations:

[0072] Identify the human voice data in the voice data according to the voice data;

[0073] Judge whether there is a conversation request including personnel other than the user bound to the hearing aid in the human voice data;

[0074] When there is the conversation request, output a bone oscillator occupancy prompt and / or output a conversation request prompt.

[0075] Further, the processor 1001 may call the audio signal processing program stored in the memory 1003 and further perform the following operations:

[0076] The step of outputting the conversation request prompt includes:

[0077] Determine the audio signal corresponding to the conversation request according to the voice data;

[0078] When receiving the stop voice collection instruction sent by the interaction device, amplify the audio signal corresponding to the conversation request;

[0079] Drive the bone oscillator of the hearing aid according to the amplified audio signal corresponding to the conversation request.

[0080] Further, the processor 1001 may call the audio signal processing program stored in the memory 1003 and further perform the following operations:

[0081] Collect voice data through the pickup microphone of the hearing aid;

[0082] Identify whether the voice data is the voice data of the bound user of the hearing aid;

[0083] When it is identified that the voice data is the voice data of the bound user, use the pickup microphone as the target signal source and re-execute the step of amplifying the target audio signal corresponding to the target signal source.

[0084] Collect voice data through the pickup microphone of the hearing aid;

[0085] Determine a switching instruction according to the voice data;

[0086] Change the target signal source according to the switching instruction and re-execute the step of amplifying the target audio signal corresponding to the target signal source.

[0087] Further, the processor 1001 can call the audio signal processing program stored in the memory 1003 and also perform the following operations:

[0088] Obtain the historical voice data of the bound user of the hearing aid;

[0089] Construct a voice recognition model associated with the bound user according to the historical voice data;

[0090] The step of determining the switching instruction according to the voice data includes:

[0091] Input the voice data into the voice recognition model to determine the switching instruction.

[0092] Further, the processor 1001 can call the audio signal processing program stored in the memory 1003 and also perform the following operations:

[0093] Collect voice data through the pickup microphone of the hearing aid;

[0094] Identify whether there is key information of concern in the voice data, and the key information of concern includes identification words and danger warning information;

[0095] When the key information of concern is identified, amplify the audio signal corresponding to the key information of concern as a new target audio signal and re-execute the step of driving the bone oscillator of the hearing aid according to the amplified target audio signal.

[0096] The following is an explanatory description of the content claimed in the claims of the present invention through specific exemplary solutions, so that those skilled in the art can better understand the protection scope of the claims of the present invention. It can be understood that the following exemplary solutions do not limit the protection scope of the present invention, but are only used to explain the present invention.

[0097] Exemplarily, referring to ​ , in an embodiment of the audio signal processing method of the present invention, the audio signal processing method includes the following steps:

[0098] Step S10: When receiving audio signals corresponding to multiple signal sources, determine the priority corresponding to each of the signal sources;

[0099] In this embodiment, the main body that executes the audio signal processing method is a hearing aid, especially a bone conduction hearing aid.

[0100] A hearing aid is an auxiliary hearing tool. After the hearing aid amplifies the audio signal to be played through a power amplifier module, it drives the bone oscillator to work. The bone oscillator directly transmits the sound signal to the auditory nerve of the user through vibration, so as to achieve the purpose that the user can hear the sound. Most users of hearing aids are hearing-impaired people with weak hearing. After the sound is amplified, they can hear these sounds, but they have higher requirements for sound clarity and content volume. A hearing aid may include a communication unit such as a Bluetooth module and can receive audio signals from different signal sources.

[0101] Due to the presence of a pickup microphone and a Bluetooth module in the hearing aid, the audio signals it receives can come from a variety of signal sources. The signal sources may include an interaction device and a pickup microphone that establish a Bluetooth connection with the hearing aid. The signal sources may also include a call module of the interaction device, a video and audio module of the interaction device, a pickup microphone of the hearing aid, etc. The hearing aid can receive audio signals corresponding to multiple signal sources at the same time. It should be understood that the reception of audio signals is a continuous process. In the case of the signal source remaining unchanged, within a certain period of time, the hearing aid will continuously receive the audio signals of this signal source. Therefore, the starting moments when the signal source sends audio signals to the hearing aid may be different. For example, when the hearing aid has already received the audio signals of one signal source, other signal sources may send audio signals to the hearing aid, so that the hearing aid is in a state of receiving audio signals corresponding to multiple signal sources.

[0102] When the hearing aid receives audio signals corresponding to multiple signal sources, determine the priority corresponding to each signal source. Before this, it is necessary to first determine the preset correspondence between the signal source and the priority.

[0103] Optionally, the preset correspondence can be pre-stored in the hearing aid, or the user can set the preset correspondence through an interaction device, including operations such as creation, modification, deletion, etc. Then, based on the Bluetooth connection with the hearing aid, the interaction device sends the set preset correspondence or the corresponding setting operation to the hearing aid, so that the hearing aid updates the previously stored preset correspondence according to the received preset correspondence or the corresponding setting operation.

[0104] Step S20: Determine the target signal source based on the priority;

[0105] In this embodiment, the hearing aid sorts the target signal sources according to the priority, and then sorts the signal sources according to the priority. According to the sorting result, a preset number of signal sources with higher priorities are selected for playback. To make the listening experience of the hearing-impaired person better, the signal source with the highest priority is used as the target signal source. Optionally, when the target audio signal corresponding to the target signal source cannot be received, the signal source with a priority lower than that of the target signal source is used as the new target signal source, and step S30 is executed.

[0106] Step S30: Amplify the target audio signal corresponding to the target signal source;

[0107] Step S40: Drive the bone oscillator of the hearing aid according to the amplified target audio signal.

[0108] In this embodiment, the target signal source is the signal source with a higher priority. To amplify the target audio signal corresponding to the target signal source, the target audio signal can be amplified by the power amplifier module of the hearing aid. Then, the bone oscillator is driven according to the amplified target audio signal, so that the bone oscillator vibrates to emit sound. The volume of the emitted sound will be higher than the volume of the original target audio signal, so that users with weak hearing can normally hear sounds that better meet their needs.

[0109] Optionally, before the target audio signal is amplified, it is also necessary to preprocess the target audio signal: If the signal source corresponding to the target audio signal is a pickup microphone, the hearing aid collects various sounds around the user in the form of voice data through the pickup microphone, converts them into audio signals, sends the useful audio signals to pre-amplification after processing, and then sends the amplified audio signals to the central control center for software and digital signal processing. The processed audio signals are sent to the power amplifier module for amplification processing, and then the bone oscillator is driven to work. The bone oscillator directly transmits the audio signals to the user's auditory nerve through vibration to achieve the purpose of hearing aid. If the signal source corresponding to the target audio signal is an interactive device that has established a Bluetooth connection with the hearing aid: The hearing aid sends or receives signals through its Bluetooth module to interact with the key device. The hearing aid processes the audio signals received through the Bluetooth module through the MCU, decodes them and then sends them to the central control center for software and digital signal processing. The processed audio signals are sent to the power amplifier module for amplification processing, and then the bone oscillator is driven to work. The bone oscillator directly transmits the audio signals to the user's auditory nerve through vibration to achieve the effect that the user can hear the audio of the interactive device more clearly.

[0110] Optionally, the signal source includes the call module of the interactive device, the audio-visual module of the interactive device, and the pickup microphone of the hearing aid. The priority of the call module of the interactive device is higher than that of the audio-visual module of the interactive device, and the priority of the audio-visual module of the interactive device is higher than that of the pickup microphone of the hearing aid. The hearing aid will preferentially use the call module of the interactive device as the target signal source: preferentially amplify the call audio signal of the interactive device and drive the bone oscillator of the hearing aid through the amplified call audio signal; followed by the audio-visual module of the interactive device; and then the pickup microphone of the hearing aid.

[0111] Based on this, in an optional implementation, the target signal source is an interactive device that has established a Bluetooth connection with the hearing aid. After the step of determining the target signal source based on the priority, it further includes: when receiving a voice collection instruction sent by the interactive device, collecting voice data through the pickup microphone of the hearing aid; and sending the voice data to the interactive device.

[0112] After determining that the target signal source is an interaction device that establishes a Bluetooth connection with the hearing aid, the hearing aid serves as a medium for its user to use the interaction device. The interaction device can be modules such as a mobile phone, a tablet, a recording device, etc. Therefore, the interaction device has a need to collect the user's voice, such as functions like calls, recordings, and voice commands. As an auxiliary hearing device, the hearing aid is worn on the user's ear for a long time. Therefore, to improve convenience, the user can use the pickup microphone of the hearing aid as the sound collection device associated with the interaction device. When the interaction device has a need to collect the user's voice, it sends a sound collection command to the hearing aid. When the hearing aid receives the sound collection command sent by the interaction device, it collects the surrounding voice data through the pickup microphone, mainly including the user's vocal data. And it sends the voice data to the interaction device.

[0113] Further, the target signal source is the call module of the interaction device. After the step of collecting voice data through the pickup microphone of the hearing aid, it further includes: identifying the vocal data in the voice data according to the voice data; determining whether there is a conversation request including a person other than the user bound to the hearing aid in the vocal data; when there is the conversation request, outputting an occupation prompt for the bone oscillator and / or outputting a conversation request prompt.

[0114] When the target signal source is the call module of the interactive device, the user may be engaged in a conversation. At this point, the hearing aid's amplifier module and bone vibrator are occupied by the audio signal from the interactive device's call module, leaving the user only able to hear the conversation voice from the interactive device. If, at this point, a voice, such as a broadcast or a nearby person, calls out to the user, the user, due to hearing impairment, cannot hear the broadcast or the call and cannot respond promptly. Therefore, when the microphone collects voice data, it identifies the human voice data within the voice data. Due to the unique nature of hearing aids, their users are generally fixed. Therefore, the user is the bound user of the hearing aid, and the voiceprint information of the bound user, i.e., the voiceprint information of the current user of the hearing aid, is pre-stored. Based on the pre-stored voiceprint information of the bound user, the voice data can be used to identify whether the voice data includes voice data of a person other than the bound user, and to identify a conversation request from the person's voice data. Alternatively, the voice data can be used to identify whether the voice data includes a conversation request, and to identify a conversation request from a person other than the bound user based on the pre-stored voiceprint information of the bound user. The conversation request is also voice data, which may include the name (name, identity, etc.) of the bound user, greetings, voice data with a sound level greater than a preset value, etc. When there is a conversation request from someone other than the bound user in the voice data, a bone vibrator occupancy prompt and / or a conversation request prompt is output. Outputting the bone vibrator occupancy prompt is for people other than the bound user. Optionally, an additional normal volume broadcast module is set on the hearing aid. Outputting the bone vibrator occupancy prompt includes playing a voice such as "The user cannot hear your call temporarily" through the broadcast module. Outputting the conversation request prompt is for the bound user.

[0115] It should be noted that users may also make conversation requests during a call. To avoid unnecessary computing power and reduce disruption to the user, these conversation requests need to be excluded. In addition, conversation requests from people other than the bound user include broadcast sounds, conversation requests from nearby people, and so on.

[0116] Exemplarily, the audio signal corresponding to the conversation request is determined based on the voice data; when a stop receiving instruction sent by the interactive device is received, the audio signal corresponding to the conversation request is amplified; and the bone vibrator of the hearing aid is driven based on the audio signal corresponding to the conversation request after amplification.

[0117] To minimize disruption to the user's conversation, the call request prompt is not displayed until the call ends. The voice data corresponding to the call request is extracted from the voice data, and voice data such as "missed call sound" can be added to generate an audio signal. Upon receiving a stop reception command from the interactive device, this audio signal is prioritized as the target audio signal, amplified, and used to activate the bone vibrator. This allows the user to immediately hear the call request and respond promptly after the call ends.

[0118] In an alternative embodiment, the target signal source is the audio - video module of the interaction device. After the step of driving the bone oscillator of the hearing aid according to the amplified target audio signal, the method further includes: collecting voice data through the pickup microphone of the hearing aid; identifying whether the voice data is the voice data of the bound user of the hearing aid; when it is identified that the voice data is the voice data of the bound user, using the pickup microphone as the target signal source, and re - executing the step of amplifying the target audio signal corresponding to the target signal source.

[0119] The interaction device can be a module such as a mobile phone, a tablet, a recording device, etc. The interaction device has a need for audio - video playback, such as functions like movies and music. When the target signal source is the audio - video module of the interaction device, the power amplifier module and the bone oscillator of the hearing aid are occupied by the audio signal of the audio - video module, and the user can only hear the audio - video audio in the interaction device. Still, voice data near the hearing aid is obtained through the pickup microphone, and it is identified whether the voice data is the voice data of the bound user of the hearing aid. When it is determined that the voice data is the voice data of the bound user, that is, the user of the hearing aid is speaking. The audio - video module of the interaction device has no need to collect the user's voice. Therefore, if the user is speaking, it means that the user has a need to communicate with the outside world. Then, the pickup microphone is used as the target signal source. As an exception to the priority, the audio signal of the pickup microphone is used as the new target signal source, and then steps S30 and S40 are re - executed. When a preset condition is met, step S10 is re - executed. The preset condition can be receiving a switching instruction, lasting for a preset time, or the pickup microphone not collecting voice data.

[0120] In the technical solution disclosed in this embodiment, when receiving the audio signals corresponding to multiple signal sources, the priority of each signal source is determined; the target signal source is determined based on the priority; the target audio signal corresponding to the target signal source is amplified; and the bone oscillator of the hearing aid is driven according to the amplified target audio signal. In this way, through the priority of the signal source, the target audio signal of the target signal source is preferentially amplified, and the bone oscillator is driven to vibrate according to the amplified target audio signal to emit the sound that the target signal source wants to transmit, which is more in line with the user's needs. And since receiving the audio signals corresponding to the signal sources is a continuous process, when the priority of the signal source corresponding to the audio signal currently being processed by the hearing aid is lower than the priority of the signal source corresponding to another newly received audio signal, the newly received audio signal will be preferentially processed, that is, the current signal source is switched to the new signal source. In this way, the priority can ensure that the sound source heard by the user meets the user's needs, and also improves the switching efficiency of the hearing aid signal source. It realizes the purpose of automatically switching the hearing aid between the hearing - aid mode and the Bluetooth mode, which is convenient for the user to use.

[0121] Optionally, referring to ​ , based on any of the above embodiments, in another embodiment of the audio signal processing method of the present invention, the audio signal processing method further includes:

[0122] Step S50: Collect voice data through the sound pickup microphone of the hearing aid;

[0123] Step S60: Determine a switching instruction according to the voice data;

[0124] Step S70: Change the target signal source according to the switching instruction, and re - execute the step of amplifying the target audio signal corresponding to the target signal source.

[0125] In this embodiment, the sound pickup microphone can obtain nearby voice data when the target signal source is any signal source. For example, when the target signal source is the call module of the interaction device, the audio - video module of the interaction device, and the sound pickup microphone, voice data can be collected through the sound pickup microphone. The voice data includes the voice data of the user or other people, and the user can trigger a switching instruction through the content of the voice data, such as switching to the next - priority target signal source, switching the sound pickup microphone as the target signal source, switching to the target signal source determined by the switching priority, etc. Change the target signal source according to the switching instruction, and re - execute Step S30 and Step S40 based on the changed target signal source. When a preset condition is met, re - execute Step S10, and the preset condition can be receiving a switching instruction, lasting for a preset time, the sound pickup microphone not collecting voice data, etc.

[0126] Optionally, obtain the historical voice data of the user bound to the hearing aid; construct a voice recognition model associated with the bound user according to the historical voice data; the step of determining the switching instruction according to the voice data includes: inputting the voice data into the voice recognition model to determine the switching instruction.

[0127] The users of hearing aids are hearing-impaired people, that is, they have hearing impairments. Many hearing-impaired people have their speech functions affected because they have been in a state where they cannot accurately receive external sounds since childhood or for a long time. Due to individual differences among each hearing-impaired person, when speaking, they may have unclear enunciation, inaccurate pronunciation, etc., and the speaking styles of each hearing-impaired person may be different. Due to the particularity of hearing-impaired people, when using a unified speech recognition model, the speech recognition of hearing-impaired people is prone to inaccuracies. Therefore, the historical voice data of the user bound to the hearing aid is obtained in advance, and a speech recognition model specific to the user bound to the hearing aid is constructed and trained based on the historical voice data. The speech recognition model is more adaptable to the speaking habits, speech rates, pronunciations, etc. of the bound user, and the accuracy of recognizing the voice data of the bound user is higher. This speech recognition model is associated and saved with the bound user. When the voice data of the bound user is input into this speech recognition model, the accuracy of the switching instruction contained in the voice data is higher.

[0128] In an alternative embodiment, voice data is collected through the microphone of the hearing aid; it is identified whether there is key information of concern in the voice data, and the key information of concern includes identification words and danger warning information; when the key information of concern is identified, the audio signal corresponding to the key information of concern is amplified as a new target audio signal, and the step of driving the bone oscillator of the hearing aid according to the amplified target audio signal is re-executed.

[0129] Voice data is collected through the microphone of the hearing aid, and it is identified whether there is key information of concern in the voice data. The key information includes identification words and danger warning information (such as warning sounds of car honks, sirens, etc. that warn of danger or indicate the presence of danger). If the key information of concern is of the speech type, such as the name of the bound user, identification words (such as "Please make way", "Please", "Be careful of danger"), etc., the user can set it through the interaction device and then send it to the hearing aid based on Bluetooth connection. The key information of concern is the voice data collected by the microphone, and the microphone will convert the collected voice data into an audio signal and send it to the next node. When the key information of concern is identified, the audio signal corresponding to the key information of concern is amplified as a new target audio signal, and step S40 is re-executed to convey the corresponding sound to the user. In this way, when there is a sound that needs to be key-concerned near the user, it can be conveyed to the user in time to avoid the user being in danger and enabling the user to better adapt to the external life.

[0130] In the technical solution disclosed in this embodiment, voice data is collected by the sound pickup microphone of the hearing aid; a switching instruction is determined according to the voice data, the target signal source is changed according to the switching instruction, and the step of amplifying the target audio signal corresponding to the target signal source is re-executed. In this way, a switching instruction representing the real-time needs of the user is determined based on the voice data, and the target signal source is changed according to the switching instruction, so that the hearing aid can convey sounds that meet the real-time needs of the user, thereby improving the accuracy of the signal source switching of the hearing aid.

[0131] In addition, an embodiment of the present invention further provides a hearing aid, which includes a memory, a processor, and an audio signal processing program stored on the memory and executable on the processor. When the audio signal processing program is executed by the processor, the steps of the audio signal processing method described in each of the above embodiments are implemented.

[0132] In addition, an embodiment of the present invention further provides a computer-readable storage medium, on which an audio signal processing program is stored. When the audio signal processing program is executed by a processor, the steps of the audio signal processing method described in each of the above embodiments are implemented.

[0133] It should be noted that in this article, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or system including that element.

[0134] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments.

[0135] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium as described above (such as ROM / RAM, magnetic disk, optical disc), and includes several instructions for causing a hearing aid to execute the methods described in each embodiment of the present invention.

[0136] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be similarly included in the patent protection scope of the present invention.

Claims

1. An audio signal processing method, characterized in that, Applied to a hearing aid, the method comprises: Upon receiving audio signals corresponding to a plurality of signal sources, determining a priority corresponding to each of the signal sources; determining a target signal source based on the priority, the target signal source being an interactive device that establishes a Bluetooth connection with the hearing aid; amplifying the target audio signal corresponding to the target signal source; driving the bone vibrator of the hearing aid according to the amplified target audio signal; After the step of determining the target signal source based on the priority, upon receiving a sound reception instruction sent by the interactive device, collecting voice data through the pickup microphone of the hearing aid; Sending the voice data to the interactive device; When the target signal source is the call module of the interactive device, identifying human voice data in the voice data, and determining whether there is a conversation request from a person other than the hearing aid-bound user; When the conversation request is present, outputting a bone vibrator occupancy prompt to persons other than the hearing aid-bound user through the broadcast module on the hearing aid; After the call ends, outputting a conversation request prompt to the hearing aid-bound user; When the target signal source is the audio and video module of the interactive device, identifying whether the voice data is human voice data of the hearing aid-bound user; If the hearing aid is bound to the user's voice data, the pickup microphone is used as the target signal source, and the step of amplifying the target audio signal corresponding to the target signal source is performed again.

2. The audio signal processing method according to claim 1, characterized in that The step of outputting a dialogue request prompt comprises: determining an audio signal corresponding to the dialogue request according to the voice data; When receiving a stop receiving instruction sent by the interactive device, amplifying the audio signal corresponding to the dialogue request; The bone vibrator of the hearing aid is driven according to the amplified audio signal corresponding to the conversation request.

3. The audio signal processing method according to claim 1, characterized in that, After the step of driving the bone vibrator of the hearing aid according to the amplified target audio signal, the method further includes: collecting voice data through the microphone of the hearing aid; determining a switching instruction according to the voice data; The target signal source is changed according to the switching instruction, and the step of amplifying the target audio signal corresponding to the target signal source is re-executed.

4. The audio signal processing method according to claim 3, wherein Before the step of determining the switching instruction according to the voice data, the method further includes: Obtaining historical voice data of the user bound to the hearing aid; Building a speech recognition model associated with the bound user based on the historical human voice data; The step of determining the switching instruction according to the voice data comprises: The voice data is input into the voice recognition model to determine the switching instruction.

5. The audio signal processing method according to claim 1, wherein After the step of driving the bone vibrator of the hearing aid according to the amplified target audio signal, the method further includes: collecting voice data through the microphone of the hearing aid; Identifying whether there is any key information in the voice data, wherein the key information includes logos and danger warning information; When the key information of concern is recognized, the audio signal corresponding to the key information of concern is amplified as a newly added target audio signal, and the step of driving the bone oscillator of the hearing aid according to the amplified target audio signal is executed again.

6. A hearing aid, characterized in that, The hearing aid includes: a memory, a processor, and an audio signal processing program stored on the memory and executable on the processor, and when the audio signal processing program is executed by the processor, the steps of the audio signal processing method according to any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium, characterized in that, An audio signal processing program is stored on the computer-readable storage medium, and when the audio signal processing program is executed by a processor, the steps of the audio signal processing method according to any one of claims 1 to 5 are implemented.

Images