CN215202006U

CN215202006U - Robot device capable of customizing simulated human voice

Info

Publication number: CN215202006U
Application number: CN202022969941.XU
Authority: CN
Inventors: 刘慧军; 刘瑞柯; 刘瑞桐
Original assignee: Shenzhen Huawei Education Technology Co ltd
Current assignee: Shenzhen Huawei Education Technology Co ltd
Priority date: 2020-12-11
Filing date: 2020-12-11
Publication date: 2021-12-17
Anticipated expiration: 2030-12-11

Abstract

The utility model provides a robot device capable of customizing and simulating human voice, which belongs to the technical field of intelligent robots and comprises a CPU, wherein the CPU is respectively connected with a distance sensor module, a light sensor module, a temperature sensor module, a voice playing module, a power management module, an LED, a storage module and a voice synthesis module, the voice synthesis module is connected with a voice recognition module for voice recognition, the voice recognition module is connected with a network communication module, the voice recognition module is connected with a voice acquisition module through the network communication module, the utility model discloses pre-process the acquired background sound by a toy terminal through a WIFI or 5G bridge, and then, the depth recognition and analysis of the human voice are realized by utilizing the cloud voice processing server cluster capacity of the voice recognition module, the customization of the human voice is realized, and text information is played for children by synthesizing the sound which is highly similar to the sound of parents through utilizing the voiceprint characteristic information of the parents, to achieve high chaperone and affinity.

Description

Robot device capable of customizing simulated human voice

Technical Field

The utility model relates to an intelligent robot technical field especially relates to a can customization simulation people's voice robot device.

Background

Due to the fact that the rhythm of life is fast, parents are busy working, and cannot accompany children at home or interact with children at home at any time outside. Therefore, a plurality of intelligent sound box products emerge in the market, so that children can simply talk with the intelligent sound box, or various information on the internet is played to the children through the sound box.

This kind of intelligent audio amplifier equipment for children accompany or study has following not enough:

1. the existing intelligent sound box product cannot enable the children of the low age to carry out interaction on more limbs.

2. As a companion product, the voice played by the sound box is unknown sound of children, so that the companion of the children is not sufficient in perception and cannot feel as a companion of parents.

SUMMERY OF THE UTILITY MODEL

The utility model provides a technical problem provide a can customization simulation people's voice robot device.

In order to solve the technical problem, the utility model provides a

The utility model provides a can customization simulation people's voice robot, includes CPU, CPU is connected with distance sensor module, light sensor module, temperature sensor module, pronunciation broadcast module, power management module, LED, storage module and speech synthesis module respectively, speech synthesis module is connected with the speech recognition module who is used for speech recognition, speech recognition module is connected with network communication module, speech recognition module is connected with the pronunciation collection module through network communication module.

Furthermore, the network communication module selects a WIFI network or a 5G network.

Furthermore, the voice playing module can dynamically adjust decibels according to the environment of the equipment.

Furthermore, the voice acquisition module is composed of a plurality of full-directional microphones.

Still further, robot device includes rotary electromagnet, head, health and head shell, the top fixed connection rotary electromagnet and the head shell of health, rotary electromagnet's top fixedly connected with head, and the head is at the head shell internal rotation, the preceding terminal surface of head is mother's head characteristic, the rear end face of head is father's head characteristic.

Furthermore, the CPU is connected with an intermediate relay, the intermediate relay is connected with the rotary electromagnet and the power management module, and the CPU controls the rotary electromagnet according to the recognized voice type when the voice recognition module recognizes voice.

Has the advantages that:

the utility model discloses a WIFI or 5G carry out the preliminary treatment back with toy terminal to the background sound of gathering as the bridge, utilize speech recognition module's high in the clouds speech processing server cluster ability to accomplish the degree of depth discernment and the analysis to the voice, let father and mother or children can be more free with this companion product dialogue interdynamic, have strengthened the intelligent perception of product. The utility model discloses utilize speech synthesis module's ability to realize customization speech synthesis, accompany the type toy and realize accomplishing that parents are not on the side also can describe for the user that child told the story with parent's sound at any time, reduce children's lonely. The utility model discloses CPU is according to the rotatory electro-magnet of speech type control of discernment during speech recognition module discernment pronunciation, CPU need not to start rotatory electro-magnet when speech recognition module discernment pronunciation is the women, CPU starts rotatory electro-magnet when speech recognition module discernment pronunciation is the male sex, rotatory electro-magnet drives the head and rotates 180, the rear end face that rotatory electro-magnet drove the head rotates to just to child for father's head characteristic, realize that the head adapts to the adjustment according to the pronunciation condition, realize head portrait and sound complete cooperation, the better anthropomorphic dummy of carrying on accompanies, help child to carry out the robot in actual conditions and accompany, let the low-age child carry out the interdynamic on more limbs.

Drawings

Fig. 1 is a schematic view of a first embodiment of the present invention;

fig. 2 is a schematic view of a second embodiment of the present invention;

fig. 3 is a schematic view of the head feature of the mother according to the second embodiment of the present invention;

fig. 4 is a schematic view of the feature of the father's head according to the second embodiment of the present invention.

Detailed Description

Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present invention, and should not be construed as limiting the present invention.

Example 1

As shown in fig. 1, a robot apparatus capable of customizing a simulated human voice includes a CPU6, a distance sensor module 1, a light sensor module 2, a temperature sensor module 3, a voice playing module 5, a power management module 7, an LED8, a storage module 9, and a voice synthesis module 11, which are respectively connected to a CPU 6;

the distance sensor module 1 monitors the approaching condition of a person, when the person reaches a set distance, the distance sensor module 1 receives a signal and transmits the signal to the CPU6, and the CPU6 controls the device to work;

the temperature sensor module 3 monitors the temperature of the equipment, and can stop working when the temperature of the equipment has a certain safety threshold value, so that the safety of the equipment is ensured;

the light sensor module 2 is used for distinguishing nighttime or daytime environments by equipment, controlling the sound playing decibel number of the voice playing module 5 and controlling the LED8 to be turned off and on at the same time;

the storage module 9 is used for storing voice voiceprint characteristics;

the voice recognition module 12 is a cloud voice processing server cluster;

the voice playing module 5 can dynamically adjust decibels according to the environment of equipment, the voice synthesizing module 11 is connected with a voice recognition module 12 for voice recognition, the voice recognition module 12 is connected with a network communication module 10, the network communication module 10 selects a WIFI network or a 5G network, the voice recognition module 12 is connected with a voice acquisition module 4 through the network communication module 10, and the voice acquisition module 4 is composed of a plurality of all-directional microphones;

the speech synthesis module 11 synthesizes the speech of the speech recognition module 12 into corresponding speech, for example, synthesizes the parental voiceprint features into parent speech with high similarity.

Example 2

Example 2 is a further modification to example 1;

as shown in fig. 2, 3 and 4, the robot device includes a rotary electromagnet 14, a head 15, a body 16 and a head housing 17, the top of the body 16 is fixedly connected with the rotary electromagnet 14 and the head housing 17, the top of the rotary electromagnet 14 is fixedly connected with the head 15, the head 15 rotates in the head housing 17, the front end surface of the head 15 is a mother head feature, the rear end surface of the head 15 is a father head feature, the head 15 can be customized to other relatives head features or cartoons according to actual needs, the CPU6 is connected with an intermediate relay 13, the intermediate relay 13 is connected with the rotary electromagnet 14 and the power management module 7, the CPU6 controls the rotary electromagnet 14 according to the recognized voice type when the voice recognition module 12 recognizes voice, the CPU6 does not need to start the rotary electromagnet 14 when the voice recognition module 12 recognizes voice as female, the CPU6 starts the rotary electromagnet 14 through the intermediate relay 13 when the voice recognition module 12 recognizes voice as male, rotatory electro-magnet 14 drives head 15 and rotates 180, and rotatory electro-magnet 14 drives the rear end face of head 15 and rotates to just to child for father's head characteristic, realizes that head 15 carries out the adaptation adjustment according to the pronunciation condition, realizes head portrait and sound complete coordination, and better simulation person of carrying on accompanies, helps child to carry out robot in actual conditions and accompanies, lets the low-age children carry out the interaction on more limbs.

When the distance sensor module 1 is used, the condition that a person approaches is monitored, when the person reaches a set distance, the distance sensor module 1 receives a signal and transmits the signal to the CPU6, and the CPU6 controls the device to work; the CPU6 starts the temperature sensor module 3 and the light sensor module 2, monitors the temperature of the equipment, and can stop working when the temperature of the equipment has a certain safety threshold value, so that the safety of the equipment is ensured; the light sensor module 2 is used for distinguishing nighttime or daytime environments by equipment, controlling the sound playing decibel number of the voice playing module 5, and meanwhile controlling the LED8 to be turned off in the daytime and controlling the LED8 to be turned on at night; firstly, a section of voice of a parent is recorded into a device through a voice acquisition module 4, under the dispatching of a CPU6, a section of voice file is transmitted to a voice recognition module 12 at the cloud end through a network communication module 10, the voice recognition module 12 recognizes the voice voiceprint characteristics of the user and then stores the voice voiceprint characteristics in a storage module 9 of a local device, a child initiates voice conversation through the voice acquisition module 4, the device recognizes the voice of the voice recognition module 12 and then uses WIFI or 5G as a bridge to preprocess the collected background voice through a toy terminal, the cloud end voice processing server cluster capacity of the voice recognition module 12 is utilized to realize deep recognition and analysis of the voice, so that the parent or the child can more freely carry out conversation interaction with the accompanying product, the intelligent perception of the product is enhanced, the feedback content required by the conversation content is matched through cloud end searching and then is sent to the device, the voice synthesis module 11 in the device synthesizes parent voice with high similarity through the parent voiceprint characteristics stored in the device, the voice is played through the voice playing module 5 of the playing device, customized voice synthesis is realized by utilizing the capability of the voice synthesis module 5, and the accompanying toy realizes that the voice of parents can be used for telling a user of a child to tell a story at any time when the parents are not around, so that the loneliness of the child is reduced; when speech recognition module 12 discerned pronunciation CPU6 according to the pronunciation type control rotary electromagnet 14 of discernment, CPU6 need not to start rotary electromagnet 14 when speech recognition module 12 discerned pronunciation and is the women, CPU6 passes through auxiliary relay 13 and starts rotary electromagnet 14 when speech recognition module 12 discerned pronunciation and is the men, rotary electromagnet 14 drives head 15 and rotates 180, rotary electromagnet 14 drives the rear end face of head 15 and rotates to just facing child for father's head characteristic, it adjusts to realize that head 15 adapts to the pronunciation condition, realize head portrait and sound complete coordination, better carry out anthropomorphic dummy and accompany, help child to carry out robot accompany in actual conditions, let the low-age child carry out the interaction on more limbs.

The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention in any way, and those skilled in the art can make many variations and modifications of the technical solution of the present invention without departing from the scope of the technical solution of the present invention.

Claims

1. A robotic device capable of customizing simulated human voice, comprising a CPU (6), characterized in that: CPU (6) are connected with distance sensor module (1), light sensor module (2), temperature sensor module (3), pronunciation broadcast module (5), power management module (7), LED (8), storage module (9) and speech synthesis module (11) respectively, speech synthesis module (11) are connected with speech recognition module (12) that are used for speech recognition, speech recognition module (12) are connected with network communication module (10), speech recognition module (12) are connected with pronunciation collection module (4) through network communication module (10).

2. A robotic device capable of customized human voice simulation according to claim 1, wherein: the network communication module (10) selects a WIFI network or a 5G network.

3. A robotic device capable of customized human voice simulation according to claim 1, wherein: the voice playing module (5) can dynamically adjust decibels according to the environment of the equipment.

4. A robotic device capable of customized human voice simulation according to claim 1, wherein: the voice acquisition module (4) is composed of a plurality of full-directional microphones.

5. A robotic device capable of customized human voice simulation according to claim 1, wherein: the robot device comprises a rotary electromagnet (14), a head (15), a body (16) and a head shell (17), wherein the top of the body (16) is fixedly connected with the rotary electromagnet (14) and the head shell (17), the top of the rotary electromagnet (14) is fixedly connected with the head (15), the head (15) rotates in the head shell (17), the front end face of the head (15) is a mother head feature, and the rear end face of the head (15) is a father head feature.

6. A robotic device capable of customized human voice simulation according to claim 5, wherein: the CPU (6) is connected with an intermediate relay (13), the intermediate relay (13) is connected with the rotary electromagnet (14) and the power management module (7), and the CPU (6) controls the rotary electromagnet (14) according to the recognized voice type when the voice recognition module (12) recognizes voice.