Intelligent voice noise reduction interaction method and system of humanoid robot

Abstract

The embodiment of the invention provides an intelligent voice noise reduction interaction method and system of a humanoid robot, and belongs to the technical field of artificial intelligence. The method comprises the steps of collecting sound source information; obtaining target sound source position information according to the sound source information; collecting audio data; obtaining target audio data according to the target sound source position information and the audio data; and completing noise reduction processing according to the target audio data. The voice recognition accuracy of the humanoid robot in a complex acoustic environment can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an intelligent voice noise reduction interaction method and system for a humanoid robot. Background Art

[0002] In the application scenarios of humanoid robots, voice interaction is an important way for them to communicate with humans. However, the environmental noise in different application scenarios is difficult to be consistent, and problems such as interference from multiple sound sources often affect the accuracy of voice recognition and the interactive experience. Summary of the invention

[0003] The main purpose of the embodiments of the present application is to provide an intelligent voice noise reduction interaction method and system for a humanoid robot.

[0004] The technical solution adopted by the present invention is:

[0005] On the one hand, an embodiment of the present invention provides an intelligent voice noise reduction interaction method for a humanoid robot, the method comprising the following steps:

[0006] Collect sound source information;

[0007] According to the sound source information, obtaining the target sound source position information;

[0008] Collect audio data;

[0009] Obtaining target audio data according to the target sound source position information and the audio data;

[0010] According to the target audio data, noise reduction processing is completed.

[0011] Furthermore, the collecting of sound source information comprises the following steps:

[0012] Obtain visual and auditory information;

[0013] Obtaining spatial position information according to the visual information and the acoustic information;

[0014] The sound source information is obtained according to the spatial position information.

[0015] Further, obtaining the target sound source position information according to the sound source information comprises the following steps:

[0016] Preset several target collection areas;

[0017] According to the target acquisition area and the sound source information, the target sound source position information is obtained.

[0018] Further, obtaining target audio data according to the target sound source position information and the audio data comprises the following steps:

[0019] Extracting speech information corresponding to the target sound source position from the audio data according to the target sound source position information;

[0020] According to the voice information, target audio data is obtained.

[0021] Further, the noise reduction process is completed according to the target audio data, comprising the following steps:

[0022] Preset neural network model;

[0023] Determining a masking value according to the neural network model;

[0024] A noise reduction process is completed according to the masking value and the target audio data.

[0025] On the other hand, an embodiment of the present invention further provides an intelligent voice noise reduction interaction system for a humanoid robot, the system comprising:

[0026] The first module is used to collect sound source information;

[0027] The second module is used to obtain the target sound source position information according to the sound source information;

[0028] The third module is used to collect audio data;

[0029] A fourth module is used to obtain target audio data according to the target sound source position information and the audio data;

[0030] The fifth module is used to complete noise reduction processing according to the target audio data.

[0031] Furthermore, the system further comprises:

[0032] Sound source localization module, used to determine the spatial location information of the speaker;

[0033] A target sound source identification module is used to match the target sound source position according to the target acquisition area;

[0034] Audio data acquisition module, used to optimize audio acquisition using automatic gain control algorithm technology;

[0035] A target audio data extraction module, used to extract target audio data;

[0036] The noise reduction processing module and the multimodal information fusion module are used to perform noise reduction processing.

[0037] Furthermore, the system also includes a visual module and an acoustic module;

[0038] The visual module includes a visual sensor; the acoustic module includes a microphone array.

[0039] On the other hand, an embodiment of the present invention also provides an intelligent voice noise reduction interaction device for a humanoid robot, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the intelligent voice noise reduction interaction method for the humanoid robot as described above is implemented.

[0040] On the other hand, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the method described above.

[0041] The embodiments of the present application include at least the following beneficial effects: The present application provides an intelligent voice noise reduction interaction method and system for a humanoid robot. The present invention collects sound source information; obtains target sound source position information based on the sound source information; collects audio data; obtains target audio data based on the target sound source position information and the audio data; and completes noise reduction processing based on the target audio data. The present invention can improve the speech recognition accuracy of a humanoid robot in a complex acoustic environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a flow chart of an intelligent voice noise reduction interaction method for a humanoid robot provided by an embodiment of the present invention;

[0043] Figure 2 is a flowchart of a method for reducing noise of intelligent speech of a humanoid robot provided by an embodiment of the present invention;

[0044] Figure 3 : is an example flow chart of a method for determining spatial position information of a humanoid robot intelligent voice provided by an embodiment of the present invention;

[0045] Figure 4 is a flowchart of a method for reducing noise of intelligent speech of a humanoid robot provided by an embodiment of the present invention;

[0046] Figure 5 is an example diagram of a noise reduction module of a humanoid robot provided by an embodiment of the present invention;

[0047] Figure 6 Schematic diagram of the system composition of a humanoid robot provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0049] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0050] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0052] The embodiments of the present invention are further described below in conjunction with the accompanying drawings.

[0053] On the one hand, the embodiment of the present invention provides an intelligent voice noise reduction interaction method for a humanoid robot, referring to Figure 1 , the method comprises the following steps:

[0054] S100, collecting sound source information;

[0055] S200, obtaining target sound source position information according to the sound source information;

[0056] S300, collecting audio data;

[0057] S400, obtaining target audio data according to the target sound source position information and the audio data;

[0058] S500: Complete noise reduction processing according to the target audio data.

[0059] The embodiment of the present invention discloses that step S100 collects sound source information, including the following steps:

[0060] S110, obtaining visual and acoustic information;

[0061] S120, obtaining spatial position information according to the visual information and the acoustic information;

[0062] S130. Obtain sound source information according to the spatial position information.

[0063] The embodiment of the present invention discloses that step S200 obtains the target sound source position information according to the sound source information, including the following steps:

[0064] S210, presetting a number of target collection areas;

[0065] S220: Obtain target sound source location information according to the target acquisition area and sound source information.

[0066] As an optional implementation, in S210, the present invention can use a coordinate system to divide several target acquisition areas according to scene characteristics. Each area can be defined by coordinate points or bounding boxes to ensure that all potential sound source locations are covered.

[0067] In S210, priority can also be set for each target collection area according to the importance of different areas. For example, some areas (such as conference rooms or rest areas) may be more important and require higher accuracy and frequent audio collection.

[0068] In S220, the present invention performs a preliminary analysis on the collected audio signal and uses a sound source localization algorithm (such as a time difference localization method, a beamforming method, etc.) to determine the preliminary location of the sound source. The identified sound source location information is compared with a preset target collection area to determine whether the sound source is located in the target area. If the sound source location is within the target area, further processing is performed.

[0069] The embodiment of the present invention discloses that step S400 obtains target audio data according to the target sound source position information and the audio data, including the following steps:

[0070] S410, extracting speech information corresponding to the target sound source position from the audio data according to the target sound source position information;

[0071] S420: Obtain target audio data according to the voice information.

[0072] As an optional implementation, in step S410, the system first selects the voice information corresponding to the position from the previously collected audio data based on the identified target sound source position information. This process involves the analysis and processing of audio signals, and the spatial feature extraction of the sound received by each microphone is performed through an algorithm to ensure that the extracted voice signal is as clear as possible and highly relevant to the target sound source. Specifically, beamforming technology is used to further focus on the target sound source, thereby improving the signal-to-noise ratio of the voice signal.

[0073] In step S420, the extracted voice information is further processed to obtain the final target audio data. The system will perform necessary format conversion and enhancement processing on the extracted voice information to ensure the clarity and comprehensibility of the voice data. At the same time, the noise reduction processing module is used to effectively suppress background noise to ensure that the output target audio data can accurately reflect the user's intention and content, thereby laying a solid foundation for subsequent intelligent voice interaction.

[0074] The embodiment of the present invention discloses that step S500 completes the noise reduction process according to the target audio data, including the following steps:

[0075] S510, presetting a neural network model;

[0076] S520, determining a masking value according to the neural network model;

[0077] S530: Complete noise reduction processing according to the masking value and the target audio data.

[0078] As an optional implementation, a neural network model suitable for audio noise reduction is designed. The model needs to be trained with a large amount of labeled audio data to learn how to extract clear speech features from noisy audio signals.

[0079] After the model training is completed, it is applied to real-time audio data. In this step, the noisy audio signal is first input to the model, and the model will output a masking value, which represents the ratio of the intensity of the background noise to the target speech within a specific frequency range. This masking value provides a basis for subsequent noise reduction processing, helping the system determine which frequency components need to be retained and which need to be attenuated.

[0080] The embodiment of the present invention combines the masking value with the target audio data and uses filtering technology to process the audio signal. The system applies an adaptive filter to the audio signal in the frequency domain and adjusts the gain of different frequencies according to the masking value, thereby reducing the noise component and enhancing the clarity of the target speech. This process ensures that the output audio signal retains the natural characteristics and intelligibility of the speech while minimizing background noise.

[0081] On the other hand, an embodiment of the present invention further provides an intelligent voice noise reduction interaction system for a humanoid robot, the system comprising:

[0082] The first module is used to collect sound source information;

[0083] The second module is used to obtain the target sound source position information according to the sound source information;

[0084] The third module is used to collect audio data;

[0085] The fourth module is used to obtain target audio data according to the target sound source position information and the audio data;

[0086] The fifth module is used to complete noise reduction processing according to the target audio data.

[0087] The intelligent voice noise reduction interactive system for a humanoid robot provided by an embodiment of the present invention further includes:

[0088] Sound source localization module, used to determine the spatial location information of the speaker;

[0089] A target sound source identification module is used to match the target sound source position according to the target acquisition area;

[0090] Audio data acquisition module, used to optimize audio acquisition using automatic gain control algorithm technology;

[0091] A target audio data extraction module, used to extract target audio data;

[0092] The noise reduction processing module and the multimodal information fusion module are used to perform noise reduction processing.

[0093] The intelligent voice noise reduction interactive system for a humanoid robot provided by an embodiment of the present invention further includes a visual module and an acoustic module;

[0094] The visual module includes a visual sensor; the acoustic module includes a microphone array.

[0095] As an optional implementation, the present invention provides an intelligent voice noise reduction interaction method and system for a humanoid robot, which determines the location of the sound source through a perception system and a microphone array, and uses a neural network model to perform noise reduction processing to improve the accuracy of voice recognition and the quality of interaction.

[0096] The technical solution of the present invention includes:

[0097] 1. Sound source localization technology: Determine the spatial location information of the speaker through the perception system and microphone array carried by the humanoid robot.

[0098] 2. Target sound source identification: According to the preset target acquisition area, match the target sound source position from the spatial position information.

[0099] 3. Audio data acquisition: The user’s voice is collected at the target sound source location through a microphone array to generate an audio data signal.

[0100] 4. Target audio data extraction: Extract the user voice corresponding to the target sound source position from the audio data signal.

[0101] 5. Noise reduction processing: Use a preset neural network model to determine the masking value of the target audio data and perform noise reduction processing.

[0102] 6. Multimodal information fusion: Combine lip movement recognition, head spatial position information, and sound source position information to generate accurate spatial position information.

[0103] 7. Beamforming technology: Adjust the main lobe of the microphone array beam to point to the target sound source, while pointing the beam null point or zero point to the interfering sound source to optimize audio collection.

[0104] 8. Dynamic gain control: Gain the speech signal collected by the target microphone group and attenuate the signals of other microphone groups.

[0105] Exemplarily, the intelligent speech noise reduction interaction system of the humanoid robot of the present invention includes a sound source localization module, a target sound source recognition module, an audio data acquisition module, a target audio data extraction module, a noise reduction processing module and a multimodal information fusion module.

[0106] The sound source localization module further includes a visual module (the visual module includes a visual sensor, such as an RGBD camera) and an acoustic module (the acoustic module includes a microphone array), which are used to determine the spatial position information of the speaker.

[0107] The target sound source identification module is used to match the target sound source position according to the target acquisition area.

[0108] The audio data acquisition module uses automatic gain control algorithm technology to optimize audio acquisition.

[0109] The noise reduction processing module uses a neural network model to determine the masking value of the target audio data and perform noise reduction.

[0110] As an optional implementation, refer to Figure 2 The noise reduction method of the humanoid robot intelligent speech of the present invention comprises:

[0111] The humanoid robot’s perception system and microphone array determine the speaker’s spatial location information;

[0112] According to the preset target acquisition area, the target sound source position is matched from the spatial position information;

[0113] The microphone array is used to collect the user's voice at the target sound source position to generate an audio data signal;

[0114] Extracting the user voice corresponding to the target sound source position from the audio data signal;

[0115] Use a preset neural network model to determine the masking value of the target audio data and perform noise reduction processing.

[0116] Optionally, refer to Figure 3 The method for determining the spatial position information of the humanoid robot intelligent voice of the present invention comprises:

[0117] Determine the head position recognition information of the user group within the space through the humanoid robot visual sensor;

[0118] According to the head position recognition information, the lip activities of the user groups in the space are recognized;

[0119] Determine the location information of the sound source in the space through a microphone array;

[0120] Multimodal information fusion is performed on lip movement and head spatial position sound source information to generate spatial position information.

[0121] As an optional implementation, refer to Figure 4 The process of the noise reduction method of the humanoid robot intelligent voice of the present invention uses a microphone array to judge the sound direction in space, and combines visual sensors to monitor the head position and lip activities, which can effectively realize multimodal fusion, thereby accurately locating the user's voice. By judging the target user's voice and the interference sound and noise source, the system can effectively separate the user's voice from the background noise, mask the interference sound, and perform noise reduction and enhancement processing on the target user's voice. The ultimate goal of this comprehensive technology is to enhance the user's voice experience and ensure clear communication of information in a complex environment.

[0122] As an optional implementation, refer to Figure 5 The noise reduction module of the humanoid robot in the embodiment of the present invention includes a first determination module, a second determination module, a first generation module, a second generation module, and an execution module.

[0123] The first determination module can determine the spatial position information of the speaker, the second determination module can determine the target sound source position information, the first generation module can generate an audio data signal, the second generation module can extract the user voice corresponding to the target position, and the execution module can perform noise reduction processing.

[0124] Optionally, refer to Figure 6The system of the humanoid robot of the present invention includes a perception system, a drive system, a decision control system and a robot computing platform. The perception system includes a visual module, a tactile module, an acoustic module, a temperature sensing module and a posture module;

[0125] The drive system includes foot module, arm module, head module, dexterous hand module and waist module;

[0126] The decision control system includes an input module, a storage module, a communication module, a judgment module, and an execution module;

[0127] The robotic computing platform includes a processor and memory.

[0128] In some embodiments, an intelligent voice noise reduction interaction method for a humanoid robot of the present invention includes the steps of collecting sound source location information, identifying target sound sources, collecting audio data, extracting target audio data, and performing noise reduction processing.

[0129] In some embodiments, the target sound source position is matched from the spatial position information according to a preset target acquisition area.

[0130] Example: In a scenario where a humanoid robot is having a voice conversation with a user, the user in the same space sends a voice control command to the humanoid robot, and the humanoid robot receives the voice control command and completes the corresponding automatic control operation. For example, a user sends a control command to the humanoid robot to "bring a bottle of water over here", and the humanoid robot responds accordingly based on the received control voice. There may be multiple people having a voice conversation at the same time in a space, for example, two people in the space are communicating with each other, and the humanoid robot user is also sending a voice control command to the humanoid robot. At this time, there is a need to determine the spatial location information.

[0131] When the space information is 1, it means that there is only one person in voice communication in the current space.

[0132] When there are multiple space information, it means that there are multiple people speaking in the current space.

[0133] In order to avoid confusion when the humanoid robot collects input voice, it is necessary to select the corresponding target collection area when the person in the space communicates with the humanoid robot by voice and before the voice signal is transmitted, and use the microphone array to determine the target sound source position to be captured from the spatial position information.

[0134] In some embodiments, lip movement recognition, head spatial position information, and sound source position information are combined to generate accurate spatial position information.

[0135] Example: By identifying lip movements, determine whether the person in the corresponding space is currently speaking, rather than the sound from other sound sources, such as the sound from the mobile phone speaker, the sound from the TV, or the sound from the radio.

[0136] By identifying the spatial position of the head, it is determined whether the person who is speaking and moving his lips is facing the humanoid robot. Generally speaking, the person who is moving his lips and facing the humanoid robot and issuing voice control commands is the main sound collection area.

[0137] The embodiment of the present invention generates spatial position information by multi-modal fusion of lip movement, head space, and sound source position.

[0138] 1. The spatial position information corresponding to the person in the space is determined by the microphone array, and the head of the humanoid robot turns to the spatial direction.

[0139] 2. Use the visual module of the head to judge the lip movement of people within the visible range, the spatial position of the head, and determine the spatial position information of the person making the sound in the space.

[0140] 3. Use the multi-mode fusion of 1 and 2 above and perform analysis to determine the spatial position information corresponding to the person who sends the voice signal in the space.

[0141] The present invention can improve the speech recognition accuracy of a humanoid robot in a complex acoustic environment, enhance the robot's adaptability to multi-user interaction scenarios, and effectively suppress the influence of interfering sound sources by dynamically adjusting the microphone array.

[0142] On the other hand, an embodiment of the present invention also provides an intelligent voice noise reduction interaction device for a humanoid robot, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the intelligent voice noise reduction interaction method for a humanoid robot as described above.

[0143] The intelligent speech noise reduction interaction device of the humanoid robot according to the embodiment of the present invention includes a memory and a processor.

[0144] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0145] The memory may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage. Among them, ROM can store static data or instructions required by the processor or other modules of the computer. The permanent storage device may be a readable and writable storage device. The permanent storage device may be a non-volatile storage device that does not lose the stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as a permanent storage device. In some other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, optical drive). The system memory may be a readable and writable storage device or a volatile readable and writable storage device, such as a dynamic random access memory. The system memory may store some or all instructions and data required by the processor at run time. In addition, the memory may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory may include a readable and / or writable removable storage device, such as a laser disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (e.g., SD card, mini SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. The computer-readable storage medium does not include carrier waves and transient electronic signals transmitted wirelessly or wired.

[0146] The memory stores executable codes, and when the executable codes are processed by the processor, the processor can execute part or all of the methods described above.

[0147] On the other hand, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above method.

[0148] It will be appreciated by those skilled in the art that all or some of the steps and systems in the disclosed method above may be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that may be used to store desired information and may be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0149] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. An intelligent voice noise reduction interaction method for a humanoid robot, characterized in that: The method comprises the following steps: Collect sound source information; According to the sound source information, obtaining the target sound source position information; Collect audio data; Obtaining target audio data according to the target sound source position information and the audio data; According to the target audio data, noise reduction processing is completed.

2. The method according to claim 1, characterized in that The collecting of sound source information comprises the following steps: Obtain visual and auditory information; Obtaining spatial position information according to the visual information and the acoustic information; The sound source information is obtained according to the spatial position information.

3. The method according to claim 1, characterized in that The step of obtaining the target sound source position information according to the sound source information comprises the following steps: Preset several target collection areas; According to the target acquisition area and the sound source information, the target sound source position information is obtained.

4. The method according to claim 1, characterized in that: The step of obtaining target audio data according to the target sound source position information and the audio data comprises the following steps: Extracting speech information corresponding to the target sound source position from the audio data according to the target sound source position information; According to the voice information, target audio data is obtained.

5. The method according to claim 1, characterized in that The noise reduction process is completed according to the target audio data, comprising the following steps: Preset neural network model; Determining a masking value according to the neural network model; A noise reduction process is completed according to the masking value and the target audio data.

6. An intelligent voice noise reduction interactive system for a humanoid robot, characterized in that: The system comprises: The first module is used to collect sound source information; The second module is used to obtain the target sound source position information according to the sound source information; The third module is used to collect audio data; A fourth module is used to obtain target audio data according to the target sound source position information and the audio data; The fifth module is used to complete noise reduction processing according to the target audio data.

7. The system according to claim 6, characterized in that The system further comprises: Sound source localization module, used to determine the spatial location information of the speaker; A target sound source identification module is used to match the target sound source position according to the target acquisition area; Audio data acquisition module, used to optimize audio acquisition using automatic gain control algorithm technology; A target audio data extraction module, used to extract target audio data; The noise reduction processing module and the multimodal information fusion module are used to perform noise reduction processing.

8. The system according to claim 6, characterized in that The system also includes a visual module and an acoustic module; The visual module includes a visual sensor; the acoustic module includes a microphone array.

9. An intelligent speech noise reduction interaction device for a humanoid robot, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the intelligent speech noise reduction interaction method for a humanoid robot as described in any one of claims 1 to 5 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the method according to any one of claims 1 to 5.

Images