METHODS AND SYSTEMS FOR FACILITATING A COLLABORATIVE WORK ENVIRONMENT

    公开(公告)号:WO2023086021A2

    公开(公告)日:2023-05-19

    申请号:PCT/SG2022/050806

    申请日:2022-11-07

    Applicant: LEMON INC.

    Inventor: ZHANG, Yuhui

    Abstract: The present disclosure describes techniques for facilitating a collaborative work environment. The techniques comprise receiving a request from a first client computing device associated with a first user in the plurality of users to establish a communication with a second user in the plurality of users, the request specifying information associated with the communication; generating and transmitting data to a second client computing device associated with the second user for display of a user interface on the second client computing device, wherein the user interface indicates an invite of communication from the first user, and the user interface comprises information about the first user, the information associated with the communication, and selectable interface elements for accepting or declining the invite; and in response to receiving an indication of acceptance by the second user, establishing a communication channel between the first user and the second user.

    CONTROLLABLE MUSIC GENERATION
    42.
    发明申请

    公开(公告)号:WO2023080847A2

    公开(公告)日:2023-05-11

    申请号:PCT/SG2022/050808

    申请日:2022-11-07

    Applicant: LEMON INC.

    Abstract: The present disclosure describes techniques for controllable music generation. The techniques comprise extracting latent vectors from unlabelled data, the unlabelled data comprising a plurality of music note sequences, the plurality of music note sequences indicating a plurality of pieces of music; clustering the latent vectors into a plurality of classes corresponding to a plurality of music styles; generating a plurality of labelled latent vectors corresponding to the plurality of music styles, each of the plurality labelled latent vectors comprising information indicating features of a corresponding music style; and generating a first music note sequence indicating a first piece of music in a particular music style among the plurality of music styles based at least in part on a particular labelled latent vector among the plurality of labelled latent vectors, the particular labelled latent vector corresponding to the particular music style.

    SUPERVISED METRIC LEARNING FOR MUSIC STRUCTURE FEATURES

    公开(公告)号:WO2023063881A2

    公开(公告)日:2023-04-20

    申请号:PCT/SG2022/050705

    申请日:2022-09-29

    Applicant: LEMON INC.

    Abstract: Devices, systems, and methods related to implementing supervised metric learning during a training of a deep neural network model are disclosed herein. In examples, audio input may be received, where the audio input includes a plurality of song fragments from a plurality of songs. For each song fragment, an aligning function may be performed to center the song fragment based on determined beat information, thereby creating a plurality of aligned song fragments. For each song fragment of the plurality of song fragments, an embedding vector may be obtained from the deep neural network. Thus, a batch of aligned song fragments from the plurality of aligned song fragments may be selected, such that a training tuple may be selected. A loss metric may be generated based on the selected training tuple and one or more weights of the deep neural network model may be updated based on the loss metric.

    SHARE BASED AUGMENTED REALITY CONTENT SERVICE SYSTEM

    公开(公告)号:WO2023014286A2

    公开(公告)日:2023-02-09

    申请号:PCT/SG2022/050510

    申请日:2022-07-19

    Applicant: LEMON INC.

    Abstract: Methods and systems are directed to a content services platform. The content services platform may include a processor and a memory storing instructions that, when executed by the processor, configure the content services platform to perform a method. The method may include receiving a request to initiate a shared session from a first client, the request including a first client identifier. Based on the received request, a session identifier may be provided to the first client associated with the first client identifier. A request from a second client may be received and may be associated with the session identifier. Thus, when message data from the first client is received, the message data may be added to a queue associated with the session identifier such that the message data may be provided from the queue to the second client based on the session identifier.

    IDENTIFYING LANGUAGE IN MUSIC
    47.
    发明申请

    公开(公告)号:WO2022182298A1

    公开(公告)日:2022-09-01

    申请号:PCT/SG2022/050093

    申请日:2022-02-25

    Applicant: LEMON INC.

    Inventor: CHOI, Keunwoo

    Abstract: The present disclosure describes techniques for identifying languages associated with music. Training data may be received, wherein the training data comprise information indicative of audio data representative of a plurality of music samples and metadata associated with the plurality of music samples. The training data further comprises information indicating a language corresponding to each of the plurality of music samples. A machine learning model may be trained to identify a language associated with a piece of music by applying the training data to the machine model until the model reaches a predetermined recognition accuracy. A language associated with the piece of music may be determined using the trained machine learning model.

    PACKET CLASSIFIER WITH COMMUTABLE MATCHING TUPLE FEATURE

    公开(公告)号:EP4498655A3

    公开(公告)日:2025-04-16

    申请号:EP24184132.9

    申请日:2024-06-24

    Applicant: Lemon Inc.

    Inventor: DONG, Xuanming

    Abstract: A packet classifier for packet classification in computer networking is provided. The packet classifier includes a packet parser, an extended key crafting logic, a match and action table, and a rule parser configured to parse predetermined rules and to identify at least one commutable matching tuple. When the rule parser identifies the at least one commutable matching tuple in the predetermined rules, the rule parser actuates the extended key crafting logic and programs the match and action table based on the identified commutable matching tuple.

Patent Agency Ranking