10 results about "Voice production" patented technology

The invention provides a voice training scheme generation method and system. The method is applied to the technical field of voice training, and comprises the following steps: acquiring voice data, voice signals and physiological feature data related to voice generation, and performing preprocessing; extracting time domain and frequency domain features from the preprocessed data, wherein the time domain features comprise fundamental frequency, peak amplitude, signal energy and the like; the frequency domain characteristics comprise a harmonic noise ratio, a fast Fourier transform median, energy distribution of a voice signal in each frequency band, a frequency spectrum centroid, a width of the frequency spectrum centroid and the like; screening high-discrimination features from the initially extracted time domain features and frequency domain features through backward / forward sequence feature selection to construct an optimized feature set, and inputting the optimized feature set into an improved S4 neural network model for training; and analyzing the voice type based on the trained model, dynamically generating a personalized voice training scheme, and performing dynamic adjustment. According to the invention, the accuracy, adaptability and robustness of the voice training scheme are improved.

An audio playback method, a failure detection method for a screen sound production component, and an electronic device. The audio playback method includes: receiving an audio playback instruction; where the audio playback instruction is used to instruct the electronic device to play a first audio; playing, in response to receiving the audio playback instruction, a detection audio by using the screen sound production component; obtaining a first parameter in a process of playing the detection audio; determining, based on the first parameter, whether the screen sound production component fails; where the first parameter is at least one of a real-time load current, a real-time load voltage, a real-time impedance, and a real-time admittance of the screen sound production component; and when the screen sound production component fails, switching the sound production component to the speaker, and playing the first audio by using the speaker.

The application discloses a sound production control method, a head-mounted display device and a computer storage medium. The sound production control method comprises the following steps: receiving a plurality of sound scanning signals of sound, and determining a low-frequency sound production sound according to each sound scanning signal; determining a correction curve corresponding to each sound scanning signal based on a pre-stored target frequency response, and collecting the correction curves to obtain a correction curve set; determining sound position information corresponding to each sound scanning signal according to an acquired instruction transceiving delay value, and performing sound production control according to the sound position information, the correction curve set and the low-frequency sound production sound. The application improves the sound production effect of the head-mounted display device at low frequencies.

Embodiments of the present disclosure provide a sound production component including a diaphragm, a magnetic circuit assembly, a coil, and a housing. The coil is connected to the diaphragm and is at least partially disposed in a magnetic gap formed by the magnetic circuit assembly, and the coil drives the diaphragm to vibrate to produce a sound after being energized. A sound outlet is provided on an inner side surface of the housing for directing a sound generated at a front side of the diaphragm out of the housing. The diaphragm comprises a main body region and a folded-ring region surrounding the main body region, the folded-ring region comprising an arc-shaped segment and a connection segment connected to the main body region. A projection of a center of the sound outlet along a vibration direction on the diaphragm is on an inner side of the arc-shaped segment.

Embodiments of the present disclosure provide a sound production component including a diaphragm, a magnetic circuit assembly, a coil, and a housing. The coil is connected to the diaphragm and is at least partially disposed in a magnetic gap formed by the magnetic circuit assembly, and the coil drives the diaphragm to vibrate to produce a sound after being energized. A sound outlet is provided on an inner side surface of the housing for directing a sound generated at a front side of the diaphragm out of the housing. The diaphragm comprises a main body region and a folded-ring region surrounding the main body region, the folded-ring region comprising an arc-shaped segment and a connection segment connected to the main body region. A projection of a center of the sound outlet along a vibration direction on the diaphragm is on an inner side of the arc-shaped segment.

1. A sound generating apparatus, comprising: a housing (100), wherein the housing (100) comprises a cable hole (110) and an inner cavity in communication with the cable hole (110); a sound generating member (200), wherein the sound generating member (200) is located in the inner cavity; an electrical connection cable (300), wherein the electrical connection cable (300) is electrically connected to the sound generating member (200), and the electrical connection cable (300) passes through the cable hole (110); and a sound-blocking member (400), wherein the sound-blocking member (400) is placed between the electrical connection cable (300) and the cable hole (110) to seal a gap between the electrical connection cable (300) and the cable hole (110). 2. The sound-generating apparatus according to claim 1, wherein a relative position between the electrical connection cable (300) and the cable hole (110) comprises a sealing position; the sound-blocking member (400) is fixedly connected to an outer wall of the electrical connection cable (300), and when the electrical connection cable (300) is moved to the sealing position with respect to the cable hole (110), the sound-blocking member (400) is configured to extend into the cable hole (110) from the outside of the cable hole (110) and slide with respect to an inner wall of the cable hole (110), to be in contact with the inner wall of the cable hole (110) to seal the space between the electrical connection cable (300) and the cable hole (110) when the electrical connection cable (300) and the cable hole (110) are in the sealing position. 3. The sound generating apparatus according to claim 1 or 2, wherein the sound-blocking member (400) comprises an adjacent region and a guide region, and the guide region is located at one end of the adjacent region that extends away from the sound-generating member (200); The radial cross-sectional area of ​​the guide region exhibits a tendency to decrease in a direction away from the adjacent region; and When the electrical connection cable (300) moves into the sealing position with respect to the cable hole (110), the sound-blocking member (400) is configured to extend into the cable hole (110) through the guide region and slide with respect to the inner wall of the cable hole (110), so that when the electrical connection cable (300) and the cable hole (110) are in the sealing position, the adjacent region is in contact with the inner wall of the cable hole (110) to seal the gap between the electrical connection cable (300) and the cable hole (110). 4. The sound generating apparatus according to any of claims 1 to 3, wherein the sound-blocking member (400) is fixedly connected to an inner wall of the cable hole (110), and the sound-blocking member (400) is in contact with an outer wall of the electrical connection cable (300). 5. The sound generating apparatus according to any of claims 1 to 4, wherein the sound blocking member (400) surrounds the entire outer periphery of the electrical connection cable (300). 6. The sound generating apparatus according to any of claims 3 to 5, wherein an inner contour of the cable hole (110) coincides with a shape of an outer contour of a radial cross-section of the electrical connection cable (300), and the sound-blocking member (400) has a uniform thickness in a circumferential direction of the electrical connection cable (300). 7. The sound generating apparatus according to any of claims 1 to 6, wherein the housing (100) comprises a sound-generating surface, a rear end surface (120) and a surrounding surface (130), the sound-generating surface being positioned opposite and separate from the rear end surface (120), the surrounding surface (130) surrounds the sound-generating surface and the rear end surface (120), the surrounding surface (130) is connected to the sound-generating surface and the rear end surface (120), and the sound-generating surface, the rear end surface (120) and the surrounding surface (130) together define, in an enveloping manner, the inner cavity; the sound-generating member (200) is connected to the sound-generating surface and / or the surrounding surface (130), one sound-emitting side of the sound-generating member (200) is opposite the sound-generating surface, the electrical connection cable (300) is located on another side of the sound-generating member (200) away from the sound-emitting side, and the cable hole (110) is positioned on the rear end surface (120); and A cable hole axis (110) is perpendicular to the rear end surface (120). 8. The sound generating apparatus according to any of claims 1 to 7, wherein the sound-blocking member (400) is elastic, and a material of the sound-blocking member (400) comprises one of foam, soft rubber, and felt; and / or the housing (100) is a soft rubber housing. 9. A cleaning device, comprising the sound generating apparatus according to any of claims 1 to 8 described above, and a main device body, wherein the sound generating apparatus is placed in the main device body. 10. The cleaning device according to claim 9, wherein the main body of the device comprises a device housing, the device housing enclosely defines an accommodation recess, the device housing is provided with a sound emission orifice in communication with the accommodation recess, the sound generating apparatus is located in the accommodation recess, and the sound generating apparatus is opposite the sound emission orifice; and The sound generating apparatus housing is connected to the device housing, or at least a partial region of the sound generating apparatus housing and the device housing are integrally formed.

The application discloses an auxiliary voice production method and system based on a convolutional neural network and a long-term short-term memory network, and relates to the technical field of image processing applications. The method comprises the following steps: constructing a prediction model framework through three neural network parts of LSTM, CNN and FCN; collecting voice production action videos, and taking frames of the voice production action videos; using part of the data files processed through frame taking to adjust parameters of the prediction model framework, and exporting a prediction model; inputting facial actions into the prediction model, and outputting semantic information of the facial actions; through combination of two deep neural networks of LSTM and CNN, processing videos of facial actions in a voice production process of a character, through combination of semantic labels of the videos, and through the ability of computer vision technology to learn video data features, and through training and optimization of the deep neural network, finally, a voice semantic prediction model with high-precision prediction ability is obtained.

This application discloses a control method, controller, atomizing device, and readable storage medium for a sound-generating structure. The control method for the sound-generating structure is applied to the atomizing device and includes: determining a sound-generating control mode for the atomizing device to control the sound-generating structure; and responding to the sound-generating control mode to control the sound-generating structure to emit a sound of the corresponding mode. By implementing the technical solution of this application, users can intuitively perceive the interaction of the atomizing device.

The application relates to an improved pathological voice generation model and a construction method thereof, which comprises the following steps: S1, using all available pathological / a / vowel speech records under normal pitch in a sound data set as a training data set; S2, a training process is divided into training of a generator and training of a discriminator, both of which are alternately performed, the generator comprises a latent mapping network module and a transposed convolution and multi-receptive field fusion module; the discriminator comprises four discriminators with different cycle settings, which are used for evaluating and training intermediate waveform outputs after each upsampling of the generator; and S3, inputting a random noise vector into the trained generator, converting the random noise vector into new audio data by the generator, performing standardization processing on the generated audio data, and repeating the above steps to generate multiple new data.

1. Name of the product in this design: Graphical User Interface for Creating and Editing Programming Files for Electronic Devices. 2. Purpose of this design: An electronic device. 3. The key design feature of this product is its graphical user interface. 4. The picture or photo that best illustrates the key design points: Design 1 front view. 5. Design 1 is designated as the basic design. 6. Purpose of the graphical user interface: Primarily used for creating and editing SB3 programming files. 7. Human-computer interaction method of graphical user interface: The upper left module of the main view to the change state diagram of Design 1 and Design 2 is the screen display area, the lower left module is the background and character area, and the large right module is the editing area; the main view of Design 1 is the code creation and editing interface, where code can be created and edited. Clicking "Shape" above the editing area in this interface will take you to the shape creation and editing interface of the change state diagram of Design 1, where shape can be created and edited; the main view of Design 2 is the code creation and editing interface, where code can be created and edited. Clicking "Sound" above the editing area in this interface will take you to the sound creation and editing interface of the change state diagram of Design 2, where sound can be created and edited. 8. Other situations requiring explanation: The gray-covered areas in each view represent the content screen, and the design for which protection is sought does not include color.