System and method for masking snoring sounds through adaptive audio-visual stimuli

Abstract

A system for masking snoring sounds includes a sleep device. The sleep device includes a sensor configured to detect a biometric data for a user, a user interface configured to generate a snore mitigation output, a processor, and a non-transitory computer readable medium comprising programming instructions. The programming instructions, when executed by the processor, cause the processor to determine whether the user is emitting a snore sound based on the biometric data and output, in response to determining the user is emitting the snore sound, the snore mitigation output. The snore mitigation output being adapted based on a characteristic of the snore sound.

Description

SYSTEM AND METHOD FOR MASKING SNORING SOUNDS THROUGH ADAPTIVE AUDIO-VISUAL STIMULICROSS-REFERENCE TO RELATED APPLICATION[00011 This application claims priority to U.S. provisional application Serial No. 63 / 747,551 filed lanuary 21, 2025, the disclosure of which is hereby incorporated in its entirety by reference herein.TECHNICAL FIELD|0002J Aspects of the disclosure generally relate to system and method for masking snoring sounds.BACKGROUND[0003 J Sleep devices, such as a Hatch Restore®, can be employed to provide ambient light and / or sound to aid a user in a peaceful sleep.SUMMARY[0004[ In an illustrative example, the present disclosure is directed to a system for masking snoring sounds, and includes a sleep device. The sleep device includes a sensor configured to detect a biometric data for a user, a user interface configured to generate a snore mitigation output, a processor, and a non-transitory computer readable medium including programming instructions. The programming instructions, when executed by the processor, cause the processor to determine whether the user is emitting a snore sound based on the biometric data, and output, in response to determining the user is emitting the snore sound, the snore mitigation output, which is adapted based on a characteristic of the snore sound.

[0005] In some aspects, the snore mitigation output is selected from among a plurality of adaptive outputs including at least one of an audible output, a visual output, or a haptic output.

[0006] In some aspects, the user interface includes a speaker, and the snore mitigation output is the audible output emitted by the speaker. The audible output is an adaptive sound signal selected from among a plurality of adaptive sound signals, each of the adaptive sound signals has a sound characteristic that is adjustable to mask the snore sound.[0007| In some aspects, the user interface includes a haptic device, and the snore mitigation output is a haptic alarm to alert the user of the snore sound.

[0008] In some aspects, the system further includes a plurality of the user interfaces to generate at least two adaptive outputs.

[0009] In some aspects, the user interface includes a light source, and the snore mitigation output is the visual output using the light source.|0010] In some aspects, the system further includes a housing to house the sensor, the user interface, the processor; and the non-transitory computer readable medium.

[0011] In some aspects, the system further includes a peripheral device that is communicatively coupled to the sleep device and includes a second sensor to detect a second biometric data transmitted to the sleep device.

[0012] In some aspects, the peripheral device includes a second user interface to output the snore mitigation output. The snore mitigation output is selected from among a plurality of adaptive outputs including at least one of an audible output, a visual output, or a haptic output. The user interface of the sleep device is configured to output a first snore mitigation output, and the second user interface of the peripheral device outputs a second snore mitigation output that is different from the first snore mitigation output.

[0013] In an illustrative example, the present disclosure is directed to a sleep device including one or more sensors configured to detect one or more biometric data for a user, a user interface including a speaker configured to generate a snore mitigation output as an audible sound, a processor, and a non-transitory computer readable medium comprising programming instructions. The programming instructions, when executed by the processor, cause the processor to determine whether the user is emitting a snore sound based on the biometric data, modify a soundcharacteristic of an adaptive sound signal based on a sound characteristics of the snore sound to mask the snore sound in response to determining the user is emitting the snore sound, and output the adaptive sound signal as the snore mitigation output using the speaker.[0014| In some aspects, the user interface includes a light source, and the snore mitigation output includes a visual output, and the programming instructions cause the processor to illuminate the light source in response to determining the user is emitting the snore sound.

[0015] In some aspects, the sensor is a microphone to detect an acoustic sound emitted by the user, as the biometric data.

[0016] In some aspects, the adaptive sound signal is selected from among a plurality of reference adaptive sounds signals.|0017] In an illustrative example, the present disclosure is directed to a method including: detecting one or more biometric data of a user using one or more sensors; determining that the user is emitting a snore sound based on the one or more biometric data; modifying a sound characteristic of an adaptive sound signal based on a sound characteristics of the snore sound to mask the snore sound in response to determining the user is emitting the snore sound; and output the adaptive sound signal as a snore mitigation output using a speaker.

[0018] In some aspects, the adaptive sound signal is selected from among a plurality of reference adaptive sounds signals.BRIEF DESCRIPTION OF THE DRAWINGS[0019| FIG. 1 illustrates a block diagram for a noise suppressing system for masking snoring sounds; and

[0020] FIG. 2 illustrates an example process for the noise suppressing system of FIG. 1.DETAILED DESCRIPTION

[0021] As required, detailed embodiments of the present invention are disclosed herein; however, it is to be understood that the disclosed embodiments are merely exemplary of the invention that may be embodied in various and alternative forms. The figures are not necessarily to scale; some features may be exaggerated or minimized to show details of particular components. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a representative basis for teaching one skilled in the art to variously employ the present invention.[00221 Snoring in shared sleeping environments can disrupt occupants. Some devices, such as a sleep device, can provide a white noise or other sound to mask the snoring. Snore masking devices can use fixed predefined noise-canceling programs for masking the sound of snoring. But such devices may not detect snoring in real time or dynamically adjusts responses.

[0023] Described herein are systems and methods for masking snoring sounds through adaptive audio-visual stimuli. In some aspects, a system includes a snore detector and a snore response generator. In some implementations, the system may include user specific features, such as haptic alarms and personalized wind-down audio- visual sequences.

[0024] The snore-detector, which may be provided in a sleep device or embedded in a wearable or peripheral device, is configured to identify snoring through, for example, sound patterns or respiratory irregularities. In one example, a library of reference snore noises may be catalogued and used for detecting a snore sound by the user.[0025J Once identified, the snore response generator is configured to output a snore mitigation output. For example, the snore response generator is configured to mask snoring sounds through various mechanisms, including ambient noise, music, white noise, or adaptive sound frequencies. In some implementations, the snore response generator may include audio to mask snoring sounds based on a frequency profile of the snore sound detected. For example, the snore response generator may output an adaptive sound signal that has an adjustable sound characteristic (e.g., frequency or tone) to mask the snore sound. Through masking, the snore does not become a uniquefrequency or volume event in the sonic environment, and thus is not a sound likely to wake up a partner of the snoring individual.

[0026] Upon receiving or detecting the snore sound, the system may match the snore sound with the appropriate reference adaptive sound, creating an instantaneous and adaptive system that is both automated, scalable and learnable. Other mask snoring sound examples may also be used and may adjust as the snoring sound change throughout a sleep period. Moreover, the adaptive system may take into account user and partner preferences, ambient noise, etc. In addition to the adaptive sound to mask the snore sound, the snore mitigation output may include a visual output (e.g., ambiance lighting to wind-down environment) and / or haptic output / alarm.

[0027] FIG. 1 illustrates a block diagram for an example noise suppression system 100 for masking snoring sounds. The noise suppression system 100 may include a sleep device 102 that is an audio-visual device providing sound and / or ambient lighting for aiding sleep. The sleep device 102 may be a standalone device configured to be arranged at or near a bed of a user. In one example, the sleep device 102 is configured to rest on a nightstand or nearby dresser. Additionally or alternatively, the sleep device 102 may be configured to hang on a wall, from a household item such as a lamp, etc.[0028| The sleep device 102 may include various types of components, processors, memory, each enclosed by a housing. In some aspects, the sleep device 102 includes a processor 104 that employs various processes, methods and algorithms. The processor 104 may execute instructions for sleep applications, including snore detection, alarms, sounds, etc. Instructions for the respective systems may be maintained in a non-volatile manner using a variety of types of computer-readable storage medium 108. The computer-readable storage medium 108 (also referred to herein as memory 108, or storage) includes any non-transitory medium (e.g., a tangible medium) that participates in providing instructions or other data that may be read by the processor 104. Computer-executable instructions may be compiled or interpreted from computer programs created using a variety of programming languages and / or technologies, including, without limitation, and either alone or in combination, Java, C, C++, C#, Objective C, Fortran, Pascal, Java Script, Python, Perl, and PL / structured query language (SQL). Likewise, a remote server 120 mayinclude a processor and controller configured to provide instructions for certain applications, including the vehicle virtual assistant.

[0029] The sleep device 102 may include an audio system having audio playback functionality through loudspeakers 112 or headphones worn by a user. The audio playback may include audio from sources including satellite radio, decoded amplitude modulated (AM) or frequency modulated (FM) radio signals, and audio signals from compact disc (CD) or digital versatile disk (DVD) audio playback, streamed audio from a mobile device, commands from a navigation system, etc. Audible commands from a virtual assistant may also be included in the audio playback, as well as noise canceling functionalities.

[0030] The sleep device 102 may include various sensors 114 and input devices including at least one microphone 110. The microphone 110 is configured to detect audio signals external from the sleep device 102. This may include acoustic sounds such as breathing, snoring, or spoken words by a user. The sensors 114 may include other forms of sensors or additional microphones. For example, the sensors 114 may include vibration sensors, thermometers, pressure sensors, optical sensors, and other devices capable of detecting human conditions. In some aspects, the sensors 144 capture biometric data including acoustic sounds of breathing and snoring; temperature; and / or pressure. The sensors 114 and microphone 110 may collect data and transmit such data for further processing to, for example, the processor 104. For example, the sensor 114 and / or microphone 110 may detect snoring of a user.

[0031] The sleep device 102 may include a wireless transceiver 116, such as a BLUETOOTH module, a ZIGBEE transceiver, a Wi-Fi transceiver, an IrDA transceiver, a radio frequency identification (RFID) transceiver, etc., configured to communicate with compatible wireless transceivers of various user devices, as well as with a communication network 118.

[0032] The communication network 118 may allow for communication between the sleep device 102 and external devices, servers, etc., including a remote server 120 and a database 122 may include one or more computer hardware processors coupled to one or more computer storage devices for performing steps of one or more methods as described herein and may enable the sleep device 102 to communicate and exchange information and data with systems and subsystems external to the device 142.

[0033] The sleep device 102 may include a user interface or display 117. The display 117 may be configured to present information to the user, such as the time of day, settings, etc. The display 117 may also be configured to receive user inputs, such as settings, preferences, etc.

[0034] The sleep device 102 may also include a light system 119. The light system 119 may include one or more light sources, such as light emitting diodes, configured to illuminate all or part of the sleep device 102. The processor 104 may illuminate the lights in certain sequences, frequencies and colors to aid in setting a sleep environment for the user. The light system 119 may be dynamically and adaptively adjusted to provide a snore mitigation output based on a detection of snoring sounds, as described herein.

[0035] The sleep device 102 may be in communication with other external or peripheral devices such as a user device 130A and a wearable device 130B via the communication network 118. The user device 130A and the wearable device 130B are collectively referred to as peripheral device 130. The user device I30A may include a user’s phone such as a smart phone, tablet, e-reader, laptop, gaming console, portable media player, virtual reality headset, etc.

[0036] The wearable device BOB may be an electronic device designed to be worn on the body. Such devices may be equipped with sensors, processors, and connectivity options to provide various functionalities. For example, the wearable device BOB may include smartwatches, fitness trackers, smart classes, cameras, clothing, earpieces, headsets, rings, head-mounted displays, location trackers, adhesive patches, etc. Further, the wearable device BOB may be any device configured to come in contact or be near a user. In one example, this may include a device to be worn on a user’s wrist, head, angle, chest, etc. In other examples, the device BOB may be embedded in a bed where the user sleeps.

[0037] The wearable device BOB may collect data via the device’s sensors and transmit such data for further processing to, for example, the sleep device 102. In one example, the wearable device BOB includes a snore detector 136. The wearable device BOB may include sensors configured to detect snoring of a user. This may be done by detecting biometric data, such as respiratory patterns and vibrations indicative of snoring. Other biometric data may also be collected by either the user device BOA or the wearable device BOB. Such data may include gestures, heart rate, temperature or other heat patterns, eye movement, etc. In some aspects, thewearable device BOB may determine whether the user is emitting the snore sound, and transmit the results to the sleep device. In addition to or in lieu of the wearable device 130B, the sleep device 102 may collect similar data by the microphone 110 and sensors 114, and may include the snore detector 136 to determine whether the user is emitting the snore sound based on the biometric data.

[0038] The wearable device 130B may also include a snore response generator 138 to output the snore mitigation output. The snore response generator 138 may be configured to react in response to an indication by the snore detector 136 that the user is snoring. For example, the snore response generator 138 may include a haptic device configured to render a haptic alarm, as the snore mitigation output, to silently wake up the user in response to the user snoring.[0039| The snore response generator 138 may also transmit an instruction to the sleep device 102 to have the sleep device emits the snore mitigation output. In one example, the snore mitigation output may include noise canceling outputs, increasing output sounds of music or white noise, to name a few. In another example, the sleep device 102 may be configured to adjust audio-visual outputs to mask disturbances caused by snoring or modify sound frequencies in real-time of the adaptive sound signal to mask snoring, as the snore mitigation output(s).[0040| While the snore detector 136 and the snore response generator 138 is described with respect to the wearable device BOB, the detector 136 and the generator 138 may be part of another suitable peripheral device 130.

[0041] In some implementations, the sleep device 102 may include the snore response generator 138 in addition to or in lieu of the peripheral device 130. Using the different user interfaces (e.g., loudspeaker 112, light system 119, or display 117), the sleep device 102 is outputs the snore mitigation output, which is adapted based on a characteristic of the snore sound.

[0042] The specific methods used to adaptively modify outputs at the sleep device 102 and / or the peripheral devices 130, may include various processing of received data from the same devices. In one example, the data may include audible data (e.g., biometric data_ that is determined to include snoring sounds. The processor 104 may detect a variety of frequency tonal balances and generate the spectral data of the snoring sound. The processor 104 may then match the snoringsound to a reference sound stored in the memory 108 having similar frequency. The reference sounds may include various sounds configured to be emitted from the sleep device 102 and / or one of the peripheral devices to offset, distract, or mask the snoring sounds from the user. The matching may include machine learning capabilities based on user feedback, or general updates from across a sample set of users to most optimally and adaptively mask snoring sounds.

[0043] In some examples, the processor 104 may additionally process the data to analyze the snoring sounds. For instance, the processor 104 may use peak RMS detection to identify the loudest instance of the audible data and use the frequency spectrum at this instance to match the frequency of the reference sound. This may be beneficial given the varying length of audible data received. In one example, the window size for the snoring sound may be approximately 1000ms with a high pass filter at 20Hz. Further processing may be performed on the received audio signals, including FFTs (Fast Fourier Transforms). In some implementations, this additional processing by the processor 104 may be implemented as part of the snore detector 136.

[0044] FIG. 2 illustrates an example process 200 for the noise suppressing system 100 of FIG. 1. The process may be carried out by the processor 104, or another remote processor via the communication network 118 and / or server 120 (e.g., the process 200 may be perform by the sleep device 102 and / or a combination of the sleep device and one or more peripheral device 130). The process 200 begins at block 205 where the processor 104 receives user sleep data (e.g., biometric data such as breathing pattern, acoustic sounds, etc.). This data may be received from any one or a number of sources. The data may come from sensors within the sleep device 102, such as the microphone 110. The data may also be provided by peripheral devices 130 such as the user device 130A and / or wearable device DOB. The data may include audio data, biometric data, etc., each which may indicate the presence of certain human behavior such as snoring.

[0045] At block 210, the processor 104, having the snore detector 136, may determine whether the received data indicates the presence of snoring. This may be done by analyzing the data, and determining whether the data exceeds certain thresholds. For example, does the data include an audio signal that exceeds a threshold decibel. If the data indicates the presence of snoring, the process 200 proceeds to block 215. If not, the process 200 proceeds back to block 205.

[0046] At block 215, in response to detecting snoring, the processor 104, having the snore response generator 138, issues instructions for an adaptive output (e.g., a snore mitigation output). Such instructions may be sent to an output mechanism or, stated differently, a user interface of the sleep device 102 or one of the peripheral devices 130 to accommodate the snoring. The output mechanism (e.g., a plurality of adaptive outputs) may be at least one of an audible, visual, or haptic output to aid in mitigating the snoring sounds. For example, the processor 104 may modify or select from a library of adaptive sounds emitted at the speaker 112 to mask the snoring via frequency matching (e.g., the processor 104 may generate an adaptive sound signal that is output as the adaptive sound). In another example, the processor 104 may send a command to the peripheral devices 130 to output a haptic alarm to the user. Other visual adjustment may be made such as adjusting the light color or intensity at the sleep device 102 using the light system 119.|0047] Accordingly, a snore detector, as well as a snore response generator is described herein and may be provided in the sleep device 102, the peripheral device 130, or a combination of the sleep device 102 and the peripheral device 130. Each device may detect snoring, as well as provide for adaptive responses in response to such snoring to aid in masking or distracting from the snoring.

[0048] In some implementations, the snore detector 136 and the snore response generator 138 may be partially or fully implemented by a special purpose computer created by configuring a general-purpose computer to execute one or more particular functions embodied in computer programs (e.g., programming instructions). The functional blocks, flowchart components, and other elements described above serve as software specifications, which can be translated into the computer programs by the routine work of a skilled technician or programmer.

[0049] As used herein, the phrase at least one of A, B, and C should be construed to mean a logical (A OR B OR C), using a non-exclusive logical OR, and should not be construed to mean “at least one of A, at least one of B, and at least one of C.”

[0050] The description of the disclosure is merely exemplary in nature and, thus, variations that do not depart from the substance of the disclosure are intended to be within the scope of the disclosure. Such variations are not to be regarded as a departure from the spirit and scope of the disclosure.

[0051] Computing devices described herein generally include computer-executable instructions, where the instructions may be executable by one or more computing devices such as those listed above. Computer-executable instructions may be compiled or interpreted from computer programs created using a variety of programming languages and / or technologies, including, without limitation, and either alone or in combination, Java™, C, C++, C#, Visual Basic, Java Script, Perl, etc. In general, a processor (e.g., a microprocessor) receives instructions, e.g., from a memory, a computer-readable medium, etc., and executes these instructions, thereby performing one or more processes, including one or more of the processes described herein. Such instructions and other data may be stored and transmitted using a variety of computer-readable media.

[0052] While exemplary embodiments are described above, it is not intended that these embodiments describe all possible forms of the invention. Rather, the words used in the specification are words of description rather than limitation, and it is understood that various changes may be made without departing from the spirit and scope of the invention. Additionally, the features of various implementing embodiments may be combined to form further embodiments of the invention.

Claims

WHAT IS CLAIMED IS:

1. A system for masking snoring sounds, comprising:a sleep device including:a sensor configured to detect a biometric data for a user;a user interface configured to generate a snore mitigation output;a processor; anda non-transitory computer readable medium comprising programming instructions that when executed by the processor, cause the processor to:determine whether the user is emitting a snore sound based on the biometric data; andoutput, in response to determining the user is emitting the snore sound, the snore mitigation output, the snore mitigation output being adapted based on a characteristic of the snore sound.

2. The system of claim 1, wherein the snore mitigation output is selected from among a plurality of adaptive outputs including at least one of an audible output, a visual output, or a haptic output.

3. The system of claim 2, wherein:the user interface includes a speaker, andthe snore mitigation output is the audible output emitted by the speaker, and the audible output is an adaptive sound signal selected from among a plurality of adaptive sound signals, each of the adaptive sound signals has a sound characteristic that is adjustable to mask the snore sound.

4. The system of claim 2, wherein the user interface includes a haptic device, and the snore mitigation output is a haptic alarm to alert the user of the snore sound.

5. The system of claim 2, further comprising a plurality of the user interfaces to generate at least two adaptive outputs.

6. The system of claim 2, wherein the user interface includes a light source, and the snore mitigation output is the visual output using the light source.

7. The system of claim 1, further comprising a housing to house the sensor, the user interface, the processor; and the non-transitory computer readable medium.

8. The system of claim 1, further comprising a peripheral device communicatively coupled to the sleep device and including a second sensor to detect a second biometric data transmitted to the sleep device.

9. The system of claim 8, wherein:the peripheral device includes a second user interface to output the snore mitigation output,the snore mitigation output is selected from among a plurality of adaptive outputs including at least one of an audible output, a visual output, or a haptic output,the user interface of the sleep device is configured to output a first snore mitigation output, andthe second user interface of the peripheral device outputs a second snore mitigation output that is different from the first snore mitigation output.

10. A sleep device, comprising:one or more sensors configured to detect one or more biometric data for a user; a user interface including a speaker configured to generate a snore mitigation output as an audible sound;a processor; anda non-transitory computer readable medium comprising programming instructions that when executed by the processor, cause the processor to:determine whether the user is emitting a snore sound based on the biometric data;modify a sound characteristic of an adaptive sound signal based on a sound characteristics of the snore sound to mask the snore sound in response to determining the user is emitting the snore sound; andoutput the adaptive sound signal as the snore mitigation output using the speaker.

11. The sleep device of claim 10, wherein:the user interface includes a light source, and the snore mitigation output includes a visual output, andthe programming instructions cause the processor to illuminate the light source in response to determining the user is emitting the snore sound.

12. The sleep device of claim 10, wherein the sensor is a microphone to detect an acoustic sound emitted by the user, as the biometric data.

13. The sleep device of claim 10, wherein the adaptive sound signal is selected from among a plurality of reference adaptive sounds signals.

14. A method, comprising:detecting one or more biometric data of a user using one or more sensors; determining that the user is emitting a snore sound based on the one or more biometric data;modifying a sound characteristic of an adaptive sound signal based on a sound characteristics of the snore sound to mask the snore sound in response to determining the user is emitting the snore sound; andoutput the adaptive sound signal as a snore mitigation output using a speaker.

15. The method of claim 14, wherein the adaptive sound signal is selected from among a plurality of reference adaptive sounds signals.

Images