Active audio devices utilizing audio recognition

Abstract

The present invention relates to an active acoustic device that utilizes audio recognition, and is characterized by including: a data input unit that inputs audio data from an external terminal; an output unit that outputs the input audio data; an audio detection unit that detects an externally generated audio signal; a determination unit that determines the audio signal detected by the audio detection unit; and a control unit that controls the output of the audio data input by the data input unit based on information determined by the determination unit.

Description

Technical Field

[0001] The present invention relates to an active audio device that utilizes audio recognition. Specifically, it relates to an audio device that can actively adjust the sound through audio recognition by means of an artificial intelligence algorithm.

Background Art

[0002] According to conventional earphones and headphones, there is a problem that the audio hearing of the user is disturbed by external noise generated while the user is listening to audio. To solve this problem, the user can control the earphones by manually turning on and off the volume adjustment and noise cancellation functions. However, the conventional volume adjustment and noise cancellation functions are cumbersome because the user has to manually adjust them according to the situation at any time. In addition, when the noise cancellation function is set according to the user's intention, there is a problem that the user cannot recognize dangerous situations. Therefore, in order to solve such problems, the present invention intends to propose an active audio device that utilizes external audio recognition and uses an artificial intelligence algorithm.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In order to solve the above problems, an object of the present invention is to provide an active audio device using an artificial intelligence algorithm.

[0005] Another object is to provide an active audio device that recognizes the surrounding environment and automatically turns on and off the sound adjustment or noise cancellation function.

[0006] Furthermore, the aim is to provide an active audio device that automatically interrupts the noise-canceling function when a danger signal is generated. [Means for solving the problem]

[0007] An active audio device comprising: an ear cap inserted at least partially into the user's ear; a data input unit for receiving audio data from an external terminal; an output unit for outputting the received audio data; an audio sensing unit for sensing an externally generated audio signal; a determination unit for analyzing the audio signal sensed by the audio sensing unit and determining the class and magnitude of the audio signal; and a control unit for controlling the output of the audio data input by the data input unit based on the information determined by the determination unit. [Effects of the Invention]

[0008] According to the present invention, it is possible to provide an audio device that can determine the user's pattern and the type and magnitude of external noise, and then turn on or off active acoustic adjustment or noise cancellation using an artificial intelligence algorithm.

[0009] Ultimately, the acoustics or noise-canceling functions are adjusted without manual intervention from the user, and an artificial intelligence algorithm, learned from surrounding conditions, can automatically adjust the acoustics. [Brief explanation of the drawing]

[0010] [Figure 1] This is a schematic diagram showing a system of an audio device according to one embodiment of the present invention. [Figure 2] This is a drawing showing an audio device according to one embodiment of the present invention. [Figure 3] This is a block diagram showing the configuration of an audio device according to one embodiment of the present invention. [Figure 4] This is a schematic diagram showing a system of an audio device according to the first embodiment of the present invention. [Modes for carrying out the invention]

[0011] An ear cap 10 that is inserted at least partially into the user's ear; Data input unit 120 for receiving audio data from an external terminal; Output unit 110 that outputs the input audio data; Audio sensing unit 130 that detects audio signals generated externally; A determination unit 140 that analyzes the audio signal detected by the audio sensing unit and determines at least one of the class and volume of the audio signal; and An active audio device characterized by including a control unit 160 that controls the output of audio data input by the data input unit 120 based on information determined by the determination unit 140.

[0012] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings, so as to be easily implemented by a person with ordinary skill in the art to which the present invention pertains. However, the present invention can be embodied in a variety of different forms and is not limited to the drawings and embodiments disclosed below. Furthermore, in order to clearly illustrate the present invention in the drawings, parts not related to the present invention have been omitted, and the same or similar reference numerals in the drawings indicate the same or similar components.

[0013] The objectives and effects of the present invention may be understood or made clearer by the following description, and detailed explanations will be omitted if it is deemed that doing so may unnecessarily obscure the gist of the invention. Therefore, the objectives and effects of the present invention are not limited to the following description.

[0014] The present invention will be described in more detail below with reference to the drawings.

[0015] Figure 1 is a schematic diagram showing a system of an audio device according to one embodiment of the present invention.

[0016] Referring to FIG. 1, an embodiment of the present invention will be briefly described. The present invention relates to an acoustic device such as an earphone or a headset that outputs audio data input from an external terminal device, and an artificial intelligence algorithm of a determination unit 140 discriminates an audio signal including noise generated externally, and adjusts the class, volume, etc. of an audio signal that can be actively heard by a user.

[0017] Hereinafter, each component will be described in more detail with reference to FIGS. 2 and 3. FIG. 2 is a drawing showing an acoustic device according to an embodiment of the present invention, and FIG. 3 is a block diagram showing the configuration of a system of an acoustic device according to an embodiment of the present invention.

[0018] Describing an embodiment with reference to FIGS. 2 and 3, the present invention may include an ear cup 10, an output unit 110, a data input unit 120, an audio sensing unit 130, a determination unit 140, a position recognition unit 150, and a control unit 160.

[0019] First, the ear cup 10 is configured to be at least partially inserted into the user's ear, and is configured to guide the audio data output through the output unit 110 to be transmitted in the inner direction of the user's ear. This may be any one of the insertion parts of various conventional earphones, and does not necessarily have to be inserted inside the user's ear, and may be provided in the form of a headset to contact the user's auricle.

[0020] The output unit 110 is configured to output the input audio data, and the data input unit 120 is configured to input audio data from an external terminal device. Specifically, the output unit 110 is configured to output audio data that can be heard by the user's ear, and finally the user can hear the audio information output from the output unit 110. The data input unit 120 is configured to input the audio data that the user intends to output through the output unit 110, and it can be any one of electronic devices that can provide audio data such as mobile phones, notebook computers, MP3 players, desktops, etc. That is, any external terminal device that can input the audio data that the user intends to listen to is possible, and it can be any one of devices that can transmit audio data through wired or wireless communication, such as the user's wired or wireless earphones, Bluetooth (registered trademark) speakers, wearable devices equipped with speakers, etc.

[0021] Hereinafter, the active audio device of the present invention can be any one of the user's wired or wireless earphones, headsets, etc., and for the sake of convenience of explanation, one embodiment will be described based on wireless earphones.

[0022] The audio sensing unit 130 is configured to sense an audio signal generated externally. Specifically, it can sense an audio signal in which a sound other than the output unit 110 that is directly transmitted through the user's hearing is generated. Specifically, the audio sensing unit 130 according to one embodiment can sense an audio signal through a microphone formed outside the user's earphone. At this time, the sensed audio signal can include all external noises, the conversation sounds of surrounding people, various environmental sounds, etc.

[0023] The audio signal detected by the audio sensing unit 130 can be transmitted to the judgment unit 140. The judgment unit 140 is configured to judge the detected audio signal and can determine one or more of the volume, class, and importance of the audio signal. More specifically, the judgment unit 140 can analyze the audio signal detected by the audio sensing unit 130 and determine one or more of the class and volume of the audio signal, and may also determine the importance of the audio signal. Here, the class is a classification set in advance by the user, and can be classified into any one of the classifications set in advance by the user through the judgment unit 140. Specifically, the class set by the user can be classified at the user's convenience so as to include one or more of the following: human voice, danger warning signal, music, everyday sounds, other noises, etc. More specifically, the judgment unit 140 can analyze the audio signal using a pre-installed artificial intelligence algorithm, and the artificial intelligence algorithm can learn from the user's manual sound adjustment and determine that the active sound device according to one embodiment of the present invention can automatically adjust the sound. Preferably, the judgment unit 140 analyzes and makes a judgment based on the external audio signal detected by the audio sensing unit 130, and together with the position recognized by the position recognition unit 150, it can make a judgment and transmit the overall judgment result of the audio signal and position to the control unit 160.

[0024] The position recognition unit 150 is configured to recognize the position of the output unit 110. The position information recognized by the position recognition unit 150 is transmitted to the judgment unit 140, which can then determine the type and volume of the audio signal based on the transmitted position information. More specifically, the position recognition unit 150 can recognize whether the user's location is outdoors or indoors, and can also recognize what kind of place the location is, such as an office, classroom, library, public transport, or public facility. More specifically, the position recognition unit 150 recognizes the location through GPS coordinates and various distance sensors, and transmits the recognized position information to the judgment unit 140. The judgment unit 140's artificial intelligence algorithm then uses pre-learned results to determine the position information, accurately determining whether the location is outdoors or indoors, and what kind of place it is. Therefore, the judgment unit 140 can determine the class and volume of an externally detected audio signal by considering the position information transmitted by the position recognition unit 150. In the aforementioned embodiment, the location of the user is determined by determining location information from the location recognition unit 150. However, in other embodiments, even without separately inserting the location recognition unit 150, the location can be determined by tracking the audio signal detected by the audio sensing unit 130, analyzing the tracked audio signal, and detecting information related to the location where the user's audio signal was detected by the artificial intelligence algorithm of the judgment unit 140. Specifically, as described above, the judgment unit 140 can analyze the detected audio signal and determine the class of the audio signal, and can determine the location based on the determined class value. Specifically, if the judgment unit 140 classifies the audio signal detected by the audio sensing unit 130 as car noise, it can recognize that the user's location is on a road or outdoors. If an audio signal classified as public transport announcements is detected, it can recognize that the user's location is on public transport. Furthermore, if sounds such as TV sounds and the sound of boiling water are detected, it can recognize that the user is indoors, and with higher precision, it may even be possible to recognize whether the location is a home or an office.Thus, while the position can be determined with more accurate coordinate values ​​through the position recognition unit 150, the user's location may also be recognized through audio signal tracking, and the output of audio data may be controlled according to that location.

[0025] The judgment unit 140 comprehensively judges the external audio signal sensed by the audio sensing unit 130 and the location information recognized by the location recognition unit 150, and can transmit control instructions based on the judgment result to the control unit 160. The control unit 160 is configured to control the output of audio data input from the data input unit 120 based on the information judged by the judgment unit 140. In detail, the control unit 160 can adjust the sound of the audio data input from the data input unit 120 based on the judgment result of the judgment unit 140 and output it to the output unit 110. That is, the sound of the output unit 110 can be adjusted automatically based on the judgment result of the judgment unit 140 without manual operation by the user. At this time, the sound to be adjusted may include the volume and reverberation of the audio data output from the output unit 110. Specifically, according to the active sound device of the present invention, the noise canceling function of the output unit 110 can be automatically turned on and off considering the user's location, the class of the external audio signal, and the input volume, and the sound such as volume and reverberation can be automatically adjusted to provide a user-customized sound adjustment system. Additionally, transparent mode may be turned on or off. More specifically, transparent mode is a function that recognizes external audio signals with the audio sensing unit 130 and outputs them to the user's ears through the output unit 110. In some cases, if an audio signal classified as a danger signal that the user must hear is detected, it is output through the output unit 110, allowing the user to hear the important audio signal.

[0026] The first embodiment and additional modified embodiments of the active acoustic device of the present invention will be described in detail below with reference to Figure 4. Figure 4 is a schematic diagram showing the system of the acoustic device according to the first embodiment of the present invention.

[0027] Referring to Figure 4, the judgment unit 140, using a pre-installed artificial intelligence algorithm, simultaneously analyzes and judges the audio signal detected by the audio sensing unit 130 and the audio data input from the data input unit 120, and instructs the control unit 160, thereby enabling the control unit 160 to control the output of the final audio data. In detail, the artificial intelligence algorithm installed in the judgment unit 140 can monitor and record the user's manual operation based on the judgment result value of the externally input audio signal. Thereafter, it can learn to actively adjust the sound based on the recorded manual operation of the user. Specifically, according to one embodiment, when an external audio signal of Noise1 is detected by the audio sensing unit 130, if the user manually adjusts the sound of the audio data that was output and listened to through the output unit 110, the artificial intelligence algorithm of the judgment unit 140 can learn by monitoring and recording the user's adjustment result. Thereafter, when an external audio signal classified in the same class is detected, it can be controlled to actively adjust the sound reflecting the user's previous sound adjustment result. Here, "sound adjustment" is a term that includes one or more of the following: volume, sound quality, and sound effects. Sound adjustment can include not only volume adjustment but also noise cancellation on / off adjustment.

[0028] In another embodiment, as shown in Figure 4, if the audio sensing unit 130 detects two external audio signals, Noise1 and Noise2, the judgment unit 140 can determine the type and circumstances of Noise1 and Noise2 by judging each audio signal. If Noise1 is determined to be an unwanted noise signal, it can be blocked to prevent it from being output to the output unit 110 that the user is listening to. If Noise2 is a dialogue sound calling to the user or a warning sound indicating a dangerous situation, it can be output to the output unit 110 for the user to hear. More specifically, the judgment unit 140 blocks all audio signals that are identified as general external noise from being output to the output unit 110 through noise cancellation. However, if it is identified as a warning sound of danger (such as a disaster notification or a car horn) or a dialogue sound from someone interacting with the user, it can be output to the output unit 110 along with the audio data. Depending on the situation, the system controls the output of dialogue sounds from both the input audio data and the output unit 110. However, if a danger warning sound is recognized, the output of the audio data may be interrupted, and only the danger warning sound may be output to the output unit 110, prioritizing the user's safety. Furthermore, when audio data and dialogue sounds are output simultaneously, the output volume and acoustics of the audio data and dialogue sounds may be automatically adjusted based on the user's usual patterns and learned results. Additionally, if the location is determined to be a library or similar via the location recognition unit 150 or audio signal analysis, the noise cancellation function can be automatically turned on. If the location is determined to be outdoors, the noise cancellation function can be turned on or off or its volume adjusted based on the user's usual patterns. Even when the noise cancellation function is on, if a danger warning sound is detected externally via the audio sensing unit 130, the noise cancellation function can be immediately disabled, and the danger warning sound can be transmitted to the user. Furthermore, if the artificial intelligence algorithm of the judgment unit 140 detects an externally generated audio signal at an intensity above a certain volume, the relevant audio signal may be transmitted to the user.Furthermore, in public transport and other situations where the user's pattern indicates that they are making regular movements, if an announcement for the name of a station is made, the noise cancellation function may be turned off to inform the user that they have arrived at a transfer station or their destination station. As mentioned above, when an audio signal classified as important based on the user's class settings, such as a warning sound or a volume above a certain level, is detected, the noise cancellation function may simply be turned off. However, according to other embodiments, transparent mode may be turned on to allow the user to recognize important audio signals more accurately and quickly.

[0029] Thus, using the active sound device of the present invention has the effect of automatically providing user-customized sound without any additional operation by the user. At the same time, it also has the effect of informing the user of dangerous situations.

[0030] The present invention relates to one embodiment, which is merely an embodiment, and those with ordinary skill in the art may be able to make various modifications and equivalent other embodiments therefrom. Therefore, the scope of the present invention is not limited by the above embodiment and the accompanying drawings. [Industrial applicability]

[0031] According to the present invention, it is possible to provide an audio device that can determine the user's pattern and the type and magnitude of external noise, and then turn on or off active acoustic adjustment or noise cancellation using an artificial intelligence algorithm.

[0032] Ultimately, the acoustics or noise-canceling functions are adjusted without manual intervention from the user, and an artificial intelligence algorithm, learned from surrounding conditions, can automatically adjust the acoustics.

Claims

1. An ear cap (10) that is inserted at least partially into the user's ear; A data input unit (120) that receives audio data from an external terminal; Output unit (110) that outputs the input audio data; Audio sensing unit (130) that detects an audio signal generated externally; A determination unit (140) analyzes the audio signal detected by the audio sensing unit and determines at least one of the class and volume of the audio signal; and A control unit (160) that controls the output of audio data input by the data input unit (120) based on the determination result by the determination unit (140); The aforementioned determination unit (140) The audio signal is analyzed by a pre-installed artificial intelligence algorithm. The aforementioned artificial intelligence algorithm is, Based on pre-learned results, the class of the audio signal is determined. Based on the determined class of the audio signal, the determination unit (140) determines that the audio signal is an unwanted noise signal, and prevents the audio signal from being heard by the user via noise cancellation. If the audio signal is determined to be a conversation sound or a warning sound, it outputs the audio signal to the output unit (110). Furthermore, the artificial intelligence algorithm monitors and records the user's manual operations when the audio signal class is determined, and learns sound adjustment and noise cancellation on / off adjustment based on the recorded user manual operations. The control unit (160) is characterized in that, when an external audio signal classified in the same class is detected thereafter, it adjusts the output of the audio data input from the data input unit (120) to reflect the learned acoustic adjustment and noise cancellation on / off adjustment results and outputs it to the output unit (110), thereby providing an active audio device.

2. The aforementioned determination unit (140) The active audio device according to claim 1, characterized in that it detects information related to the location where the audio signal was sensed, based on the determined class of the audio signal.

3. The aforementioned artificial intelligence algorithm is, The system analyzes the sensed audio signal to determine at least one of the class and volume of the audio signal, The active acoustic device according to claim 1, characterized in that it learns acoustic adjustment based on user feedback on the determined result value.

4. The system further includes a position recognition unit (150) that recognizes the position of the output unit (110); The active audio device according to claim 3, characterized in that the position information recognized by the position recognition unit (150) is transmitted to the determination unit (140), and the determination unit (140) determines the class and volume of the audio signal considering the transmitted position information.

5. The class of the aforementioned audio signal is, The active sound device according to claim 1 or 2, characterized in that it is classified into one of the classifications specified and set in advance by the user.

Images