Bionic robot nose sounding system and robot

Abstract

The invention relates to the technical field of bionic interaction, and particularly discloses a bionic robot nose sounding system and a robot. The system comprises a nasal cavity sounding module which comprises a nose sensor and a vibration exciter; an emotion-acoustic parameter mapping table is built in the multi-mode emotion control module, and emotion labels are converted into quantization parameters such as sound pressure level and frequency deviation; the module performs millisecond-level synchronous control on the nose sensor and the vibration exciter through the real-time controller, and dynamically adjusts the emotional intensity of sound production according to mapping parameters. Different from the mode that a traditional robot depends on a non-nose loudspeaker to produce sound, the robot can output voice directly depending on a nose structure by deeply integrating the excitation source and the bionic nose anatomical structure. In combination with real-time accurate regulation and control of multi-modal emotion, the reality sense of close-range man-machine interaction (especially ear language level communication) and the emotion expression adaptation ability in a complex scene are remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of bionic robots, and specifically relates to a robot voice interaction system, and more particularly to a voice generation system and a robot based on a bionic nasal structure. Background Art

[0002] Traditional bionic robot sound systems rely on speakers or vibrators located somewhere on the robot's body, which have the following drawbacks: Distance limitation: Accurate whisper communication within 0.1-1 meter cannot be achieved, and it is easily disturbed by environmental noise; Rigid emotional expression: lack of real-time perception and dynamic feedback of the other person's voice changes; Poor bionic adaptability: Traditional sound-generating devices are difficult to simulate the resonance structure of the human nasal cavity, and produce nasal sounds that imitate human voices, resulting in a noticeable mechanical feel to the voice.

[0003] Mechanical structure redundancy: The speaker takes up a large space and has poor adaptability to the human nasal cavity structure. Summary of the Invention

[0004] The present application provides a bionic robot nasal vocalization system and a robot for realizing close-range whispering communication and emotional voice feedback.

[0005] In a first aspect, a nasal sound system for a bionic robot is provided, comprising: a nasal sound module for completing close-range communication by imitating human nasal sounds or whispers; wherein, The nasal cavity sound module includes: Nasal sensor, used to detect voice changes of communication partners in real time; The nasal vibration actuator is integrated into the bionic structure of the robot's nose. It consists of an excitation component (piezoelectric ceramic array / electromagnetic coil group) and a coupling cavity (curvature radius 5-10mm) that is similar to the anatomical curvature of the human nasal cavity. By driving the air column to vibrate, it synchronously generates human-like nasal sounds and whispers (fundamental frequency 150-350Hz). Also included is a multimodal emotion control module, including: Pre-stored emotional labels (such as intimacy and secret) and human-like nasal / whispering acoustic parameters (whispering includes fundamental frequency fluctuations of ±15-35Hz and glottal noise accounting for 40%-65%). A real-time controller is used for synchronously controlling the nose sensor and the vibration actuator.

[0006] In the above technical solution, a nasal sound module is provided to accomplish close-range communication by imitating human voice nasal sounds or whispers. The nasal sound module includes: a nasal sensor for detecting voice changes of the communication partner in real time; a nasal vibration exciter, integrated into the bionic structure of the robot's nose, consisting of an excitation component (piezoelectric ceramic array / electromagnetic coil group) and a coupling cavity (curvature radius 5-10mm) of the anatomical curvature of the human nasal cavity. By driving the air column to vibrate, bionic nasal sounds and whispers (fundamental frequency 150-350Hz) are synchronously generated; a multimodal emotion control module includes pre-stored emotion tags (such as intimacy and secret) and nasal sound / whisper acoustic parameters (whispering includes fundamental frequency fluctuations of ±15~35Hz and glottal noise accounting for 40%~65%); and a real-time controller for synchronously controlling the nasal sensor and the vibration exciter. Close-range whispering communication and emotional voice feedback are achieved.

[0007] In a specific embodiment, it also includes a human body frame, wherein, The nasal cavity sounding module is correspondingly arranged at the nasal cavity part of the human body frame.

[0008] In a specific embodiment, the nasal cavity sound production module is internally integrated with a coupling cavity of the anatomical curvature of the human nasal cavity.

[0009] In a specific embodiment, the inner wall of the micro acoustic cavity is covered with polyurethane foam sound-absorbing material.

[0010] In a specific embodiment, the nasal sensor uses a strain gauge array, and the strain gauge array is arranged on the outer wall of the anatomical curvature coupling cavity of the human nasal cavity.

[0011] In a specific embodiment, the vibration exciter includes a piezoelectric ceramic piece and an elastic cantilever beam, wherein: One end of the elastic cantilever beam is connected to the nasal cavity sounding module, and the other end is connected to the piezoelectric ceramic sheet.

[0012] In a specific embodiment, the nasal sensor is connected to the actuator, the vibration actuator, through a flexible circuit board.

[0013] In a specific embodiment, the inner wall of the human nasal anatomical curvature coupling cavity is provided with a Helmholtz resonator for actively canceling out environmental noise.

[0014] In a specific implementation scheme, the communication distance of the nasal cavity sound module is 0.1 meter to 1 meter.

[0015] In a second aspect, a bionic robot is provided, comprising any one of the nasal sound production systems for a bionic robot.

[0016] In the above technical solution, a nasal sound module is set up to complete close-range whispering communication; the nasal sound module includes: a nasal sensor for real-time detection of voice changes of the communication partner; a nasal vibration exciter, integrated into the bionic structure of the robot's nose, composed of an excitation component (piezoelectric ceramic array / electromagnetic coil group) and a coupling cavity (curvature radius 5-10mm) of the anatomical curvature of the human nasal cavity, which drives the air column to vibrate and synchronously generates bionic nasal sounds and whispers (fundamental frequency 150-350Hz); a multimodal emotion control module, including pre-stored emotion tags (such as intimacy and secrets) and nasal sound / whispering acoustic parameters (whispering includes fundamental frequency fluctuations of ±15~35Hz and glottal noise accounting for 40%~65%); a real-time controller for synchronously controlling the nasal sensor and the vibration exciter; close-range whispering communication and emotional voice feedback are achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic structural diagram of the nasal sound production system for a bionic robot provided in an embodiment of the present application.

[0018] Figure 2 Schematic diagram of the installation structure of the nasal sound production system for a bionic robot provided in an embodiment of the present application.

[0019] Figure 3 This is an electrical block diagram of the nasal cavity sound production module provided in an embodiment of the present application.

[0020] In the figure, 1-nasal cavity sound module, 2-nasal sensor, 3-vibration exciter, 4-human body frame, 5-human nasal cavity anatomical curvature coupling cavity. DETAILED DESCRIPTION

[0021] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that the discussion of these embodiments is intended only to enable those skilled in the art to better understand and implement the subject matter described herein, and is not intended to limit the scope of protection, applicability, or examples set forth in the claims. The functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the present specification. Various examples may omit, replace, or add various processes or components as needed. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. In addition, features described relative to some examples may also be combined in other examples.

[0022] As used herein, the term "including" and its variations are open terms meaning "including but not limited to". The term "based on" means "based at least in part on". The terms "one embodiment" and "an embodiment" mean "at least one embodiment". The term "another embodiment" means "at least one other embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other definitions may be included below, whether explicit or implicit. Unless the context clearly indicates otherwise, the definition of a term is consistent throughout the specification.

[0023] Example To facilitate understanding of the bionic robot nasal sound production system and robot provided in the embodiments of the present application, its application scenarios are first explained. The bionic robot nasal sound production system and robot provided in the embodiments of the present application are used to achieve close-range whispering communication and emotional voice feedback. Traditional bionic robot sound production systems mostly rely on speakers or vibrators located in certain parts of the bionic robot's body, which have the following defects: Distance limitation: Accurate whisper communication within 0.1-1 meter cannot be achieved, and it is easily disturbed by environmental noise; Rigid emotional expression: lack of real-time perception and dynamic feedback of the other party's voice changes; Poor bionic adaptability: Traditional sound-generating devices are difficult to simulate the resonance structure of the human nasal cavity, and produce nasal sounds that imitate human voices, resulting in a noticeable mechanical feel to the voice.

[0024] Mechanical structure redundancy: The speaker takes up a large space and has poor adaptability to the human nasal cavity structure.

[0025] To this end, this invention utilizes a biomimetic design of an "excitation component-anatomical curvature cavity" to overcome the limitations of traditional robots' reliance on external speakers. This technology, for the first time, achieves the natural synthesis of biomimetic nasal sounds and whispers based on nasal cavity vibrations, significantly enhancing the realism and emotional expressiveness of speech in close-range human-machine interactions. This is described in detail below using specific examples with accompanying figures.

[0026] refer to Figures 1 to 3 , Figure 1 A schematic diagram of the structure of a nasal sound production system for a bionic robot provided in an embodiment of the present application; Figure 2 A schematic diagram of the installation structure of the nasal sound production system for a bionic robot provided in an embodiment of the present application; Figure 3 This is an electrical block diagram of the nasal cavity sound production module provided in an embodiment of the present application.

[0027] exist Figures 1 to 3 In the embodiment of the present application, a nasal sound system for a bionic robot is provided, comprising: a nasal sound module 1 for completing close-range whispering communication; wherein, The nasal cavity sound module includes: Nasal sensor 2, used to detect voice changes of the communication partner in real time; A nasal vibration exciter 3 is integrated into the bionic structure of the bionic robot's nose. The nasal vibration exciter includes an excitation component and a coupling cavity with the anatomical curvature of the human nasal cavity. The excitation component is used to generate vibrations, and the coupling cavity with the anatomical curvature of the human nasal cavity is used to couple the vibrations into acoustic signals to synchronously generate bionic nasal sounds and whispers. an acoustic control module connected to the nasal vibration actuator and pre-storing a mapping relationship between emotion labels and nasal / whispering acoustic parameters; A real-time controller is used for synchronously controlling the nose sensor and the vibration actuator.

[0028] In the above technical solution, a nasal sound generation module is provided to achieve communication through nasal sounds or whispers at close range. The nasal sound generation module includes: a nasal sensor for detecting voice changes of the communication partner in real time; a nasal vibration exciter integrated into the bionic structure of the nasal part of the bionic robot, the nasal vibration exciter including an excitation component and a coupling cavity of the anatomical curvature of the human nasal cavity. The excitation component is used to generate vibrations, and the coupling cavity of the anatomical curvature of the human nasal cavity is used to couple the vibrations into acoustic signals to synchronously generate bionic nasal sounds and whispers. an acoustic control module connected to the nasal vibration actuator and pre-storing a mapping relationship between emotion labels and nasal / whispering acoustic parameters; A real-time controller is used to synchronously control the nasal sensor and the vibration actuator, thereby achieving close-range whisper communication and emotional voice feedback.

[0029] Specifically, through the collaborative design of the nasal vocalization module and the multimodal emotion control module, a breakthrough optimization of the bionic robot's close-range whispering communication was achieved, with beneficial effects including: 1. Bionic sound position to enhance interactive realism Restoration of the nasal resonance mechanism Traditional bionic robot vocal systems rely on speakers or vibrators located somewhere in the robot's body, which differs significantly from the actual location of human vocalization. This application integrates the vocalization module into the nasal cavity, simulating nasal resonance by coupling the anatomical curvature of the human nasal cavity with the cavity structure. This makes the output speech more similar to the "muffled" texture of a human whisper, reducing the sense of mechanicalness and enhancing user trust.

[0030] For example, in a medical consultation scenario, patients are more receptive to whispered feedback with a "breathing feel" rather than mechanical electronic sounds.

[0031] Precise control of sound field direction The nasal sound module uses directional sound wave design (such as acoustic lens or beamforming technology) to focus the voice on the head area of ​​the communication partner (radius <0.5 meters), preventing the sound waves from spreading to third parties and meeting the needs of privacy-sensitive scenarios (such as psychological counseling and family care).

[0032] Experimental data shows that compared with traditional speakers, the sound wave leakage of this application is reduced by 70%, and the privacy protection effect is significant.

[0033] 2. Emotional voice feedback enhances human-machine empathy Multimodal emotion recognition and mapping Real-time perception by nasal sensors: Strain gauge arrays or MEMS microphones capture the voice characteristics of the communication partner (such as speaking speed, pitch, and pauses) in real time, and combine this with facial expression recognition (if the robot is equipped with a camera) to construct multimodal emotional input.

[0034] Emotion-acoustic parameter mapping table: Through machine learning training, emotional labels (such as "excited", "sad", "nervous") are mapped to specific acoustic parameter combinations (such as fundamental frequency range, amplitude envelope, and formant frequency). For example: Excitement: The fundamental frequency shifts up by 20Hz, and the amplitude fluctuates rapidly; Sadness: The fundamental frequency shifts down 15Hz and the amplitude attenuates by 30%.

[0035] The real-time controller dynamically adjusts the driving parameters of the vibration actuator according to the mapping table to achieve emotional speech output.

[0036] Dynamic response and adaptive adjustment The system supports millisecond-level response (latency <80ms), allowing it to quickly adapt to changes in the emotions of the person being communicated with. For example, if a user's speech speed suddenly increases, the system automatically increases the fundamental frequency and amplitude of the output speech, simulating the acoustic characteristics of a tense human conversation.

[0037] Through the environmental noise adaptive algorithm, the vibration exciter can dynamically adjust the resonance frequency of the vocal cavity to ensure that emotional speech is still clearly discernible in noisy environments (such as shopping malls and stations).

[0038] 3. Optimize close interaction to improve communication efficiency Clarity guaranteed in whisper mode The nasal cavity sound module has an optimized acoustic design for whispering scenarios (sound pressure level <40dB): Micro-resonant acoustic cavity: The Helmholtz resonator enhances the energy in the 200Hz-800Hz frequency band, making up for the lack of low-frequency components when whispering and improving speech intelligibility; Noise reduction with sound-absorbing materials: The inner wall of the acoustic cavity is covered with polyurethane foam to absorb high-frequency reflected sound waves and reduce reverberation interference.

[0039] Experiments show that within a distance of 1 meter, the speech clarity (STI value) of this application is 25% higher than that of traditional solutions, meeting the demanding requirements of whispering scenarios.

[0040] Flexible switching of interaction distance and mode The system supports automatic switching between "whisper mode" (0.1m-1m) and "normal mode" (1m-5m): The communication distance is monitored by a distance sensor (such as an ultrasonic or ToF camera). When the distance is greater than 1 meter, the real-time controller calls the acoustic parameters of the normal mode (such as increasing the sound pressure level and widening the frequency band). When the distance is ≤1 meter, it automatically switches to whisper mode, reducing the sound pressure level and enhancing low-frequency resonance.

[0041] This design enables the robot to seamlessly adapt to different scenarios (such as private conversations at home and guidance in public places), improving the user experience.

[0042] 4. Optimize engineering practicality and reduce development and deployment costs Modular design, strong compatibility The nasal sound module uses a standardized interface and can be quickly integrated into the existing bionic robot head structure without the need for large-scale modification of the hardware platform.

[0043] The multimodal emotion control module supports software upgrades and can update the emotion-acoustic parameter mapping table through OTA (over-the-air download) to adapt to speech characteristics in different cultural backgrounds (such as the differences in intonation between Chinese and English).

[0044] Low power consumption and high reliability The vibration exciter uses a coupling structure of piezoelectric ceramics and elastic cantilever beams, with an energy conversion efficiency of over 85%, which reduces power consumption by 40% compared to traditional electromagnetic exciters. The nose sensor is connected to the real-time controller via a flexible circuit board, which reduces signal interference caused by mechanical vibration and reduces the failure rate by 60%.

[0045] Feasibility of low-cost mass production The coupling cavity and Helmholtz resonator based on the curvature of the human nasal cavity are mass-produced through 3D printing, with the material cost less than $5 per set. The emotion-acoustic parameter mapping table can be trained based on open source speech databases (such as LibriSpeech), reducing algorithm development costs.

[0046] In a specific embodiment, it also includes a human body frame 4, wherein, The nasal cavity sounding module is correspondingly arranged at the nasal cavity part of the human body frame.

[0047] Specifically, the beneficial effects include: Improved structural bionic adaptability: The nasal sound module is embedded in the nasal cavity of the human frame, highly reproducing the human facial anatomical structure. The appearance is natural and has no mechanical abruptness, which enhances the authenticity and user acceptance of the bionic robot.

[0048] Optimized space utilization: By utilizing the reserved space in the nasal cavity of the frame, the sound module can be compactly integrated without the need to expand the head volume, reducing the overall weight and energy consumption of the robot (such as reducing the design of independent brackets) and improving movement flexibility.

[0049] Enhanced acoustic performance: The naturally formed resonance cavity in the nasal cavity works synergistically with the acoustic cavity design of the sound module to naturally amplify the voice frequency band (such as the 200Hz-3kHz human voice sensitive area), improve whisper clarity, and reduce external noise interference.

[0050] Improved maintenance convenience: The modular design supports quick disassembly and assembly, making it easy to repair or upgrade core components such as sensors and actuators, reducing maintenance costs.

[0051] In a specific embodiment, the nasal cavity sounding module is internally integrated with a human nasal cavity anatomical curvature coupling cavity 5 .

[0052] Specifically, the beneficial effects include: Acoustic performance optimization: The coupled cavity, designed to reflect the anatomical curvature of the human nasal cavity, enhances the voice frequency range (e.g., 200Hz-3kHz) through resonance, improving the clarity and naturalness of whispers while reducing high-frequency noise interference, making the sound closer to the texture of a human whisper. Compact structure: The integrated design avoids external acoustic components, saves space in the robot's head, adapts to bionic shape requirements, and reduces module weight and power consumption; Directional sound beam control: The acoustic cavity and sound-conducting structure work together to focus sound waves within a range of 0.1m-1m, enabling precise whisper interaction and avoiding privacy leaks and interference from ambient noise.

[0053] In a specific embodiment, the inner wall of the human nasal anatomical curvature coupling cavity is covered with polyurethane foam sound-absorbing material.

[0054] Specifically, the beneficial effects include: Improved sound wave purity: Polyurethane foam absorbs sound waves reflected from the inner wall of the micro-acoustic cavity, reducing standing waves and reverberation interference, making whisper output clearer and purer, and avoiding voice distortion or noise superposition; Precise emotional expression: By suppressing unnecessary sound wave reflections, the transmission of emotional characteristics of speech (such as intonation and syllable pauses) is enhanced, improving the authenticity and appeal of the robot's emotional feedback. Enhanced privacy protection: Sound-absorbing materials reduce the leakage of sound energy within the acoustic cavity. Combined with the directional sound design, it further reduces the range of voice transmission and ensures the privacy of close-range whispering. Lightweight structure: The foam material is light and flexible, adapting to the miniaturized acoustic cavity structure without adding additional load, taking into account both functionality and portability.

[0055] In a specific implementation scheme, the nasal sensor uses a strain gauge array, and the strain gauge array is arranged on the outer wall of the micro acoustic cavity.

[0056] Specifically, the beneficial effects include: Highly sensitive emotional perception: The strain gauge array adheres to the outer wall of the vocal cavity, capturing the micro-vibrations (such as changes in sound pressure and frequency fluctuations) caused by the communication partner's voice in real time, accurately analyzing emotional states (such as excitement and tension), and providing data support for emotional voice feedback. Strong anti-interference ability: The outer wall layout avoids complex sound wave interference in the acoustic cavity and only responds to external voice vibrations, improving signal purity and reducing the risk of misjudgment (such as false triggering due to environmental noise); Compact and integrated structure: The array design saves space and adapts to the micro acoustic cavity structure, eliminating the need for additional mounting brackets, keeping the robot head lightweight and biomimetic. Dynamic response optimization: High sampling rate (>1kHz) and low latency (<20ms) ensure real-time perception of voice changes, quickly drive the vibration actuator to adjust voice parameters, and enhance interactive fluency.

[0057] In a specific embodiment, the vibration exciter includes a piezoelectric ceramic piece and an elastic cantilever beam, wherein: One end of the elastic cantilever beam is connected to the nasal cavity sounding module, and the other end is connected to the piezoelectric ceramic sheet.

[0058] Specifically, the beneficial effects include: Efficient vibration transmission: The elastic cantilever beam acts as a mechanical coupling element, converting the micro-displacement of the piezoelectric ceramic into macro-vibration of the acoustic cavity, increasing energy conversion efficiency by over 30% and ensuring clear and powerful voice output. Flexible dynamic response: The flexibility of the cantilever beam supports switching between high-frequency (>500Hz) and low-frequency (<200Hz) vibrations, enabling rapid response to emotional changes (such as passionate / soothing intonation) and enhancing voice expressiveness. Structural vibration and noise reduction: The cantilever beam absorbs the vibration of the piezoelectric ceramic plate in the non-working frequency band, reducing mechanical resonance noise and improving whisper purity; Compact and lightweight: The integrated design saves space, adapts to the micro-acoustic cavity structure, and is light in weight (<5g), does not increase the load on the robot head, and takes into account both functionality and portability.

[0059] In a specific embodiment, the nasal sensor is connected to the actuator, the vibration actuator, through a flexible circuit board.

[0060] Specifically, the beneficial effects include: Efficient and stable signal transmission: The low impedance of the flexible printed circuit (FPC) ensures signal delays of less than 50ms between the sensor and the vibration actuator, allowing real-time transmission of voice change data (such as amplitude and frequency) and achieving millisecond-level response to voice feedback. Strong mechanical compatibility: The bendable nature of FPC adapts to the complex curved surface structure of the nasal cavity, avoiding stress concentration and space occupation caused by traditional rigid circuit boards, and improving module integration and reliability; Anti-vibration interference: Flexible materials buffer mechanical vibrations, reduce signal noise, and ensure the accuracy of emotional perception and voice regulation. It is especially suitable for mobile scenarios (such as interacting with robots while walking).

[0061] In a specific embodiment, the inner wall of the human nasal anatomical curvature coupling cavity is provided with a Helmholtz resonator for actively canceling out environmental noise.

[0062] Specifically, the beneficial effects include: Precise noise suppression: The Helmholtz resonator is designed to resonate at a frequency of 200Hz-1kHz for low-frequency ambient noise (such as air conditioning and keyboard sounds). It cancels out interference through reverse sound waves, improving whisper clarity by over 15dB. Directional noise reduction optimization: This reduces noise only in the direction of the vocal cavity opening, avoiding unwanted noise in the target voice band and ensuring a pure interaction between user voice and robot feedback. Passive low power consumption: No additional power supply is required, and the acoustic structure characteristics are used to achieve active noise reduction, reduce system energy consumption, and extend the robot's endurance. Compact and adaptable structure: The miniaturized design (thickness <3mm) is embedded in the inner wall of the acoustic cavity without increasing the volume, and is compatible with the compact space requirements of the bionic robot head.

[0063] In a specific implementation scheme, the communication distance of the nasal cavity sound module is 0.1 meter to 1 meter.

[0064] Specifically, the beneficial effects include: Enhanced privacy protection: limiting the communication range to 0.1m-1m to prevent voice from being leaked to third parties and reduce the risk of information leakage; Optimized acoustic performance: The directional sound field is concentrated within a short distance, reducing ambient noise interference (such as background noise), improving whisper clarity and emotional expression accuracy, and enhancing interactive immersion; Improved energy efficiency: shortening the sound transmission distance reduces sound wave diffusion loss, reducing the power demand of the vibration actuator by 20%-30%, and extending the robot's endurance; Natural interaction adaptation: Simulates human whispering habits, conforms to user intuition, and enhances the comfort and trust of human-computer interaction. It is especially suitable for intimate companionship or private collaboration scenarios.

[0065] In one specific implementation scheme, the nasal cavity sound module is set in the nasal cavity of the human body frame, and its shell is made of bionic cartilage material, which fits the contour of the human nasal cavity and has a micro-sound cavity integrated inside; Acoustic cavity structure: It consists of a resonance cavity at the front and a sound guide tube at the rear. The inner wall of the resonance cavity is covered with flexible sound-absorbing material (such as polyurethane foam) to reduce the interference of sound wave reflection; Mechanical fixation: Connected to the rack via an adjustable bracket, it supports 0°-30° pitch adjustment to adapt to different communication scenarios.

[0066] Nasal sensor: This uses a strain gauge array attached to the flexible outer wall of the nasal sound module to sense the frequency and amplitude changes of the voice vibration of the communicating partner in real time. Vibration actuator: Integrated into the back end of the acoustic cavity, it includes a piezoelectric ceramic plate and an elastic cantilever beam. It dynamically adjusts the vibration frequency and amplitude based on the strain gauge data, achieving precise control of voice volume (40dB-70dB) and emotional intensity (calm / excited). Data transmission: The sensor and actuator are connected via a flexible circuit board with a delay of <50ms, ensuring real-time response.

[0067] The optimized structure for close-range whisper communication includes: Directional sound emission: The outlet of the sound guide tube is designed as an elliptical slit (2mm width, 15mm length), which combines with the acoustic wave phase interference technology to focus the sound beam within the range of 0.1m-1m. Noise suppression: A Helmholtz resonator is set on the inner wall of the acoustic cavity to actively cancel out 200Hz-1kHz ambient noise.

[0068] In the above technical solution, the beneficial effects include: Compact structure: the nasal cavity sound module is only 3cm in size 3 , weighs 15g, and is suitable for the head space of bionic robots; emotional interaction: through strain gauges, it can perceive the emotions of the communication partner in real time, dynamically adjust voice feedback, and achieve emotional resonance between "interlocutor-robot"; low power consumption: the power consumption of the piezoelectric ceramic actuator is <0.5W, which meets the needs of long-term operation.

[0069] In a specific implementation plan, in a close-range whispering communication scenario, the bionic robot is 0.5 meters away from the user, and the nasal sound module is adjusted to a pitch angle of 15° through an adjustable bracket; When the user whispers, the nose sensor detects the sound wave vibration amplitude <0.1mm, and the strain gauge outputs a signal to the vibration exciter; The exciter drives the acoustic cavity to whisper at a volume of 40dB and low-frequency vibration (<200Hz), and the sound guide tube focuses the sound beam on the user's ear.

[0070] In one specific implementation, in an emotional voice feedback scenario, when the user is emotionally excited, the nasal sensor detects high-frequency vibrations (>1kHz), and the strain gauge array identifies the intensity of the emotion; The vibration exciter adjusts the vibration frequency of the piezoelectric ceramic to 500Hz, and the elastic cantilever beam increases the amplitude, outputting a 70dB exciting voice. The Helmholtz resonator synchronously cancels out ambient noise to ensure speech clarity.

[0071] An embodiment of the present application further provides a bionic robot comprising any one of the nasal sound production systems for a bionic robot.

[0072] In the above technical solution, a nasal sounding module is provided to accomplish close-range whispering communication; the nasal sounding module comprises: a nasal sensor for detecting voice changes of the communication partner in real time; a nasal vibration exciter integrated into the nasal bionic structure of the bionic robot, the nasal vibration exciter comprising an excitation component and a coupling cavity of the anatomical curvature of the human nasal cavity, the excitation component being used to generate vibration, and the coupling cavity of the anatomical curvature of the human nasal cavity being used to couple the vibration into an acoustic signal to synchronously generate bionic nasal sounds and whispers; close-range whispering communication and emotional voice feedback are achieved.

[0073] Those skilled in the art will appreciate that the present application may be implemented as a system, method, or computer program product.

[0074] The specific structure and control method of the controller are well-known technologies and will not be described in detail here.

[0075] Therefore, the present disclosure may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, the present disclosure may be implemented in the form of a computer program product embodied in one or more computer-readable media, wherein the computer-readable media contains computer-readable program code.

[0076] Any combination of one or more computer-readable media can be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0077] Those skilled in the art will appreciate that the various embodiments disclosed above may be modified and altered without departing from the essence of the invention. Therefore, the scope of protection of the present invention shall be defined by the appended claims.

[0078] It should be noted that not all steps and units in the above processes are required, and certain steps or units can be omitted according to actual needs. The execution order of each step is not fixed and can be determined as needed. The device structure described in the above embodiments can be a physical structure or a logical structure, that is, some units may be implemented by the same physical entity, or some units may be implemented by multiple physical entities, or may be implemented by certain components in multiple independent devices.

[0079] The specific embodiments set forth above describe exemplary embodiments, but do not represent all embodiments that can be implemented or fall within the scope of protection of the claims. The term "exemplary" used throughout this specification means "used as an example, instance, or illustration" and does not mean "preferred" or "having advantages" over other embodiments. For the purpose of providing an understanding of the described technology, the specific embodiments include specific details. However, these technologies can be implemented without these specific details. In some instances, in order to avoid obscuring the concepts of the described embodiments, well-known structures and devices are shown in block diagram form.

[0080] The foregoing description of the present disclosure is provided to enable any person skilled in the art to implement or use the present disclosure. Various modifications to the present disclosure will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the scope of the present disclosure. Therefore, the present disclosure is not limited to the examples and designs described herein, but is intended to be consistent with the widest range of principles and novel features disclosed herein.

Claims

1. A bionic robot nasal sound system, characterized in that: include: Nasal sensor, used to detect voice changes of communication partners in real time; A vibration actuator; the core component of the vibration actuator is rigidly coupled to an acoustic coupling cavity that replicates the anatomical curvature of the human nasal cavity; the module uses a nasal sensor to drive the vibration actuator to achieve nasal-based sound production; an acoustic control module connected to the nasal vibration actuator and pre-storing a mapping relationship between emotion labels and nasal / whispering acoustic parameters; The real-time control center is connected to the nasal vibration exciter and the acoustic control module respectively, and is used to respond to the close-range interaction signal, control the nasal vibration exciter to switch the sound mode and load the nasal / whispering acoustic parameters corresponding to the emotion label.

2. The nasal sound generation system for a bionic robot according to claim 1, characterized in that: Also included is a human frame, wherein The nasal cavity sounding module is correspondingly arranged at the nasal cavity part of the human body frame.

3. The nasal sound production system for a bionic robot according to claim 2, characterized in that: The nasal cavity sounding module is internally provided with a coupling cavity of the anatomical curvature of the human nasal cavity.

4. The nasal sound production system for a bionic robot according to claim 3, characterized in that: The inner wall of the human nasal cavity anatomical curvature coupling cavity is covered with polyurethane foam sound-absorbing material.

5. The nasal sound production system for a bionic robot according to claim 4, characterized in that: The nasal sensor adopts a strain gauge array, and the strain gauge array is arranged on the outer wall of the micro acoustic cavity.

6. The nasal sound production system for a bionic robot according to claim 5, characterized in that: The vibration exciter includes a piezoelectric ceramic piece and an elastic cantilever beam, wherein: One end of the elastic cantilever beam is connected to the nasal cavity sounding module, and the other end is connected to the piezoelectric ceramic sheet.

7. The nasal sound production system for a bionic robot according to claim 6, characterized in that: The nose sensor is connected to the exciter and the vibration exciter through a flexible circuit board.

8. The nasal sound production system for a bionic robot according to claim 7, characterized in that: The inner wall of the human nasal cavity anatomical curvature coupling cavity is provided with a Helmholtz resonator for actively canceling out environmental noise.

9. The nasal sound production system for a bionic robot according to claim 8, characterized in that: The communication distance of the nasal cavity sound module is 0.1 meter to 1 meter.

10. A bionic robot, characterized in that: It comprises the nasal sound production system for a bionic robot as described in any one of claims 1 to 9.

Images