Abstract: A voice recognition method, device, and a server are provided. The method includes: receiving a user voice; determining a wake-up voice of a wake-up word in the user voice, according to an acoustic feature of the user voice; and labeling the wake-up voice with a silence identifier; and ignoring the wake-up voice based on the silence identifier during voice recognition. As such, when a complex decoding algorithm is used to recognize the user voice, recognition of the wake-up word that is irrelevant to an instruction of the user is omitted, thus reducing the data amount to be processed by the decoding algorithm and improving the efficiency of voice recognition.

Abstract: The present utility model relates to a building structure, and in particular to a self-heat preservation building structure applied to extremely severe cold regions.

Abstract: The present disclosure proposes a speech processing method and a cloud-based speech processing apparatus. The speech processing method includes: acquiring a piece of speech to be recognized collected by a terminal; performing a speech recognition on the piece of speech to be recognized; detecting whether the piece of speech to be recognized ends during the speech recognition; and feeding back a recognized result of the piece of speech to be recognized to the terminal when it is detected that the piece of speech to be recognized ends.

Abstract: The present disclosure provides a speech data processing method and apparatus, a device and a storage medium, wherein the method comprises: a client obtains speech data, uses a speech wakeup engine to perform wakeup recognition for the obtained speech data, and stores the obtained speech data in a cyclic buffer queue; the client obtains a wakeup recognition result returned by the speech wakeup engine upon completion of the wakeup recognition, and if the wakeup recognition result is acknowledged wakeup and it is determined that there occurs a case of oneshot currently, determines an interception starting position and obtains buffer data in the cyclic buffer queue from the interception staring position to an end of the queue, the buffer data at least including the content to be recognized; the client sends the buffer data to a speech recognition engine so that the speech recognition engine performs speech recognition for the content to be recognized in the buffer data.

Abstract: The present disclosure proposes a method and an apparatus for converting English speech information into a text. The method may include: receiving the English speech information inputted by a user, determining a target speech recognition model according to a preset algorithm, and identifying original phonemes of the English speech information by applying the target speech recognition model; performing a matching on the original phonemes by applying a phonetic model generated by pre-training English texts and a preset probability model, and determining a target phoneme matched successfully; and acquiring a target English text corresponding to the target phoneme, and displaying the target English text on a speech conversion textbox.

Abstract: The present disclosure provides a method and a device for recognizing a text segmentation position. The method includes: receiving a continuous voice message inputted by a user, and recognizing the continuous voice message to generate a text message corresponding to the continuous voice message; analyzing the text message to determine an interval position, and sequentially inserting a sentence end and sentence begin sign at each interval position; calculating a segmentation value corresponding to the sentence end and sentence begin sign inserted at a present interval position according to a preset algorithm; and determining whether the segmentation value is greater than a preset threshold, and determining the present interval position as a segmentation position when the segmentation value is greater than the preset threshold.

Abstract: Embodiments of the present disclosure provide a method for controlling a smart device, a computer device and a non-transitory computer readable storage medium. The method includes performing speech recognition on a speech signal acquired by the smart device; determining whether a control instruction corresponding to the speech signal matches with a present operation scene of the smart device; and adjusting an operation state of the smart device according to the control instruction when the control instruction matches with the present operation scene.

Abstract: The present disclosure provides a wake-on-voice method, a terminal and a storage medium. The method includes: acquiring a wake-up voice configured to wake up a smart terminal; performing an analysis on an acoustic feature of the wake-up voice by using a preset acoustic model and a preset wake-up word recognition network of the smart terminal, so as to acquire a confidence coefficient of the acoustic feature of the wake-up voice with respect to an acoustic feature of a preset wake-up word; determining whether the confidence coefficient falls in a preset range of moderate confidence coefficients, if yes, uploading the wake-up voice to a remote server; and determining whether a linguistic feature obtained by analyzing the wake-up voice using a linguistic model matches to a linguistic feature of the preset wake-up word, if yes, receiving an instruction to wake up the smart terminal generated by the remote server.

Abstract: The present disclosure provides a speech recognition method and device. The method includes: receiving a speech signal; decoding the speech signal according to an acoustic model, a language model and a decoding network established in advance, and dynamically adding a blank unit in a decoding process to obtain an optimum decoding path with the added blank unit, in which the acoustic model is obtained based on connectionist temporal classification training, the acoustic model includes basic pronunciation units and the blank unit, and the decoding network includes a plurality of decoding paths consisting of the basic pronunciation units; and outputting the optimum decoding path as a recognition result of the speech signal.

Abstract: The present disclosure provides a method and a device for processing a speech based on artificial intelligence. The method includes: grading a current frame included in a speech packet to be decoded by using an acoustic model to obtain a grading result; identifying whether the current frame is a quasi-silent frame according the grading result; and skipping the current frame and not decoding the current frame if the current frame is the quasi-silent frame. In the present disclosure, before the current frame included in the speech pocket to be decoded is decoded, it is identified whether to decode the current frame according to the grading result obtained with the acoustic model. When there is no need to decode the current frame, the current frame is skipped. Thus, a redundancy decoding may be avoided, a speed of decoding is improved and recognition of the speech packet to be decoded is expedited.

Abstract: The present disclosure discloses a method including: performing a silence detection on a speech to be decoded; cutting the speech to be decoded off to obtain a target speech if detecting that the speech to be detected is a silent speech; resetting tail features of the target speech with preset tail features of silent frames; and performing a CTC decoding process on the target speech reset. In embodiments, when a large number of blank frames are carried in the speech to be decoded, the speech to be decoded is cut off, and the tail features of the target speech is placed with the tail features of the silent frames such that there may be one CTC peak when the CTC decoding process is performed on the tail features of the target speech. Therefore, a last word of text content may be displayed rapidly on a screen.

Abstract: The invention features a composition, such as a medical device, that is coated with activated protein C (APC).

Abstract: A portable toilet assembly has a tent and a pedestal device. The tent is composed of multiple frame loops and a cover mounted on the multiple frame loops together. The tent is collapsible. The pedestal device is composed of an upper armrest frame, a lower holding frame and a receptacle mounted on the lower holding frame. The upper arm frame and the lower holding frame are detachable from each other and respectively foldable. Thereby, the portable toile assembly can be disassembled conveniently and respectively diminished in its parts to ideal portable sizes.

Abstract: A disposable urine collecting device includes a main body, an attachment member mounted on the main body, and two binding straps mounted on the main body. Thus, the disposable urine collecting device will not produce odorous smell during long-term utilization. Therefore, the nurse or caretaker does not need to clear the disposable urine collecting device immediately, thereby saving work time.

Abstract: The present invention provides novel methods of preventing, diagnosing, and treating Critical Limb Ischemia (CLI), using eNOS polypeptides and polynucleotides to modulate eNOS activity in cells. Wild-type and mutant eNOS polypeptides, and polynucleotides encoding such polypeptides, are provided for use in the methods of the present invention. The eNOS mutant polypeptides of the present invention have at least one mutation corresponding to a site in a functional domain of a mammalian eNOS that is phosphorylated in cells.

Abstract: A portable worklight having at least two base sections that are operable between open and closed positions. The base sections are pivotally connected and when in a closed position, the base sections nest together. When in an open position, the base sections support said worklight in an upright position by providing opposingly located support sections.

Abstract: A halogen light fixture that houses at least one halogen lamp and is mountable to a support surface. The fixture includes an elongated housing having opposing ends and an interior space in which the halogen light source located. The fixture is mounted to a surface by mounts that secure the fixture to the support surface. The mounts are also opposingly located on the housing and are adapted to releasably engage a plurality of locations on a surface of the housing which causes the housing to tilt is a predetermined manner thereby allowing light to be directionally positioned.

Abstract: A portable worklight having at least two base sections that are operable between open and closed positions. The base sections are pivotally connected and when in a closed position, the base sections nest together. When in an open position, the base sections support said worklight in an upright position by providing opposingly located support sections.

Abstract: A halogen shop light having an elongated housing defining an interior space and mountable to a support surface and which includes an external receptacle. The light also includes a light source comprised of a housing, handle, lens, halogen lamp, and outwardly extending post which terminates in a ball like free end. A second post extending from the housing is also provided. The second post has inner and outer sleeves which are rotatably connected. There is also a socket in the second post which receives the ball-like free end to form an universally rotatable ball and socket connection. Wiring for energizing the lamp and the external receptacle is further provided and the wiring is placed in a channel which travels through the posts and ball.

Abstract: A worklight mounting system having a post extending from a support and a light having a catch. The post is insertable into the catch and is releasably secured within the catch by the coaction between a groove and at least one roller. The coaction there between prevents axial movement while permitting rotational movement there between.