SPEAKING PRACTICE SYSTEM WITH RELIABLE PRONUNCIATION EVALUATION

    公开(公告)号:US20240347054A1

    公开(公告)日:2024-10-17

    申请号:US18399876

    申请日:2023-12-29

    IPC分类号: G10L15/187 G06N3/02 G10L25/51

    CPC分类号: G10L15/187 G06N3/02 G10L25/51

    摘要: Goodness of pronunciation (GOP) evaluation techniques with improved reliability are presented. A data preprocessing server operates a data pre-processing system and a GOP evaluation system. The data pre-processing system includes a phonetic symbol generation system and an audio recording preprocessing system. Based on a practice text as well as an audio recording of the user reading the practice text, the phonetic symbol generation system generates phonetic symbols, and the audio recording preprocessing system generates audio data. The GOP evaluation system scores the audio recording based on the phonetic symbols and the audio data. The phonetic symbol generation system operates an artificial intelligence model, which generates the phonetic symbols in response to the fact that the practice text includes polyphonic words. Polyphonic words are words with several pronunciations due to their parts of speech, or special words which are numbers or place names.

    Data storage system and global deduplication method thereof

    公开(公告)号:US11709609B2

    公开(公告)日:2023-07-25

    申请号:US17195551

    申请日:2021-03-08

    IPC分类号: G06F3/06 H04L67/1097

    摘要: A data storage system and a global deduplication method thereof are provided. The data storage system includes multiple storage devices and one dispatch device. The dispatch device divides an original data corresponding to a data writing request into at least one data chunk. The dispatch device performs a summary calculation on one data chunk, so as to generate a representative value. The dispatch device performs a first distribution calculation on the representative value, so as to determine a destination location corresponding to the representative value. The dispatch device transmits the data chunk and the representative value to at least one destination storage device among the storage devices through a communication network according to the destination location. The at least one destination storage device checks the representative value, so as to determine whether to store the data chunk in a storage space of the at least one destination storage device.

    SMOKE DETECTION SYSTEM AND SMOKE DETECTION METHOD

    公开(公告)号:US20230177938A1

    公开(公告)日:2023-06-08

    申请号:US17739225

    申请日:2022-05-09

    摘要: The present disclosure discloses a smoke detection system and a smoke detection method. The smoke detection system includes a camera, a storage unit, and a processor. The camera acquires a current image and a previous image. The storage unit stores a plurality of modules. The processor is coupled with the camera and executes the plurality of modules. The processor generates a difference image based on the current image and the previous image. The processor inputs the current image and the difference image to a semantic segmentation model so that the semantic segmentation model outputs a smoke confidence map. The smoke confidence map is generated based on whether a current environment is a dark environment or a bright environment. The processor analyzes the smoke confidence map to determine whether a smoke event occurs in the current image. Therefore, a reliable smoke detection function can be achieved.

    Method and device for facial image recognition

    公开(公告)号:US11216648B2

    公开(公告)日:2022-01-04

    申请号:US16807292

    申请日:2020-03-03

    发明人: Hao Sun

    IPC分类号: G06K9/00 G06K9/62 G06N3/08

    摘要: A method for facial image recognition is provided. A plurality of original facial images are received. A plurality of standard facial images corresponding to the original facial images are generated through a standard face generation model. A recognition model is trained by using the original facial images and the standard facial images. The recognition model is tested by using the original facial image test set and a standard facial image test set until the recognition model recognizes that the first accuracy rate of the original facial image test set is higher than a first threshold value and the second accuracy rate of the standard facial image test set is higher than a second threshold value. The original facial image test set is composed of the original facial images obtained by sampling, and the standard facial image test set is composed of the standard facial images obtained by sampling.

    Method for vehicle blind zone detection

    公开(公告)号:US10977947B2

    公开(公告)日:2021-04-13

    申请号:US16278213

    申请日:2019-02-18

    发明人: Juan He

    摘要: A method for vehicle blind zone detection, applied to an electronic device coupled to one or more cameras arranged on a vehicle, the method comprising: setting a capture zone in a current frame image captured by the camera and detecting an object entering the capture zone in the current frame image, wherein the object meeting a capture criterion and a location information of the object meeting the capture criterion are added into a tracking list; performing tracking operations on an existing object, which has been detected and thus added to the tracking list, in one or more previous frame images preceding the current frame image captured by the camera, to obtain a new location information of the existing object in the current frame image, and determining whether to have the existing object remained in the tracking list in accordance with the new location information of the existing object and the detection scope; and making a warning determination in accordance with the location information in the current frame image for all the objects remained in the tracking list.

    Non-volatile memory apparatus and reading method thereof

    公开(公告)号:US10783032B2

    公开(公告)日:2020-09-22

    申请号:US15662254

    申请日:2017-07-27

    摘要: A non-volatile memory apparatus includes an error checking and correcting (ECC) decoding circuit, a main buffer circuit, a multiplexer, and an interface circuit. The ECC decoding circuit decodes an original codeword to obtain a decoded codeword. The main buffer circuit is coupled to the ECC decoding circuit for receiving and storing a first data portion of the decoded codeword. The multiplexer's first input end is coupled to the output end of the main buffer circuit. The second input end of the multiplexer is coupled to the output end of the ECC decoding circuit. The interface circuit is coupled to the output end of the multiplexer and receives the first data portion from the multiplexer to provide the first data portion to a host.

    Energy regulation circuit and operation system utilizing the same

    公开(公告)号:US10649513B2

    公开(公告)日:2020-05-12

    申请号:US15647449

    申请日:2017-07-12

    发明人: Tze-Shiang Wang

    摘要: An energy regulation circuit including a first voltage regulator, a processor, a second voltage regulator, and a controller is provided. The first voltage regulator adjusts an input voltage to generate an adjustment voltage. The processor increases the adjustment voltage according to the input voltage to generate a boost voltage. An energy accumulator is charged according to the boost voltage. The second voltage regulator adjusts the boost voltage to generate an operation voltage. The controller operates according to the operation voltage.