中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

18 records (took 0.012 seconds)

    Audio-Visual Separation of On-Screen Sounds Based on Machine Learning Models
    1.
    发明申请
    Audio-Visual Separation of On-Screen Sounds Based on Machine Learning Models 有权

    公开(公告)号：US20220310113A1

    公开(公告)日：2022-09-29

    申请号：US17214186

    申请日：2021-03-26

    Applicant: Google LLC

    Inventor： Efthymios Tzinis ,  Scott Wisdom ,  Aren Jansen ,  John R. Hershey

    IPC: G10L25/57 ,  G06K9/00 ,  G06K9/62 ,  G10L25/30 ,  G06N3/08

    Abstract: Apparatus and methods related to separation of audio sources are provided. The method includes receiving an audio waveform associated with a plurality of video frames. The method includes estimating, by a neural network, one or more audio sources associated with the plurality of video frames. The method includes generating, by the neural network, one or more audio embeddings corresponding to the one or more estimated audio sources. The method includes determining, based on the audio embeddings and a video embedding, whether one or more audio sources of the one or more estimated audio sources correspond to objects in the plurality of video frames. The method includes predicting, by the neural network and based on the one or more audio embeddings and the video embedding, a version of the audio waveform comprising audio sources that correspond to objects in the plurality of video frames.

    Minimum-Example/Maximum-Batch Entropy-Based Clustering with Neural Networks
    2.
    发明申请
    Minimum-Example/Maximum-Batch Entropy-Based Clustering with Neural Networks 审中-公开

    公开(公告)号：US20200372295A1

    公开(公告)日：2020-11-26

    申请号：US16880456

    申请日：2020-05-21

    Applicant: Google LLC

    Inventor： Aren Jansen ,  Ryan Michael Rifkin ,  Daniel Ellis

    IPC: G06K9/62 ,  G06N20/00

    Abstract: A computing system can include an embedding model and a clustering model. The computing system input each of the plurality of inputs into the embedding model and receiving respective embeddings for the plurality of inputs as outputs of the embedding model. The computing system can input the respective embeddings for the plurality of inputs into the clustering model and receiving respective cluster assignments for the plurality of inputs as outputs of the clustering model. The computing system can evaluate a clustering loss function that evaluates a first average, across the plurality of inputs, of a respective first entropy of each respective probability distribution; and a second entropy of a second average of the probability distributions for the plurality of inputs. The computing system can modify parameter(s) of one or both of the clustering model and the embedding model based on the clustering loss function.

    Training Machine-Learned Models for Perceptual Tasks Using Biometric Data
    5.
    发明申请
    Training Machine-Learned Models for Perceptual Tasks Using Biometric Data 有权

    公开(公告)号：US20220130134A1

    公开(公告)日：2022-04-28

    申请号：US17428659

    申请日：2020-01-16

    Applicant: Google LLC

    Inventor： Aren Jansen ,  Malcolm Slaney

    IPC: G06V10/774 ,  G06V10/80 ,  G06V40/10

    Abstract: Generally, the present disclosure is directed to systems and methods that train machine-learned models (e.g., artificial neural networks) to perform perceptual or cognitive task(s) based on biometric data (e.g., brain wave recordings) collected from living organism(s) while the living organism(s) are performing the perceptual or cognitive task(s). In particular, aspects of the present disclosure are directed to a new supervision paradigm, by which machine-learned feature extraction models are trained using example stimuli paired with companion biometric data such as neural activity recordings (e g electroencephalogram data, electrocorticography data, functional near-infrared spectroscopy, and/or magnetoencephalography data) collected from a living organism (e.g., human being) while the organism perceived those examples (e.g., viewing the image, listening to the speech, etc.).

    Diffusion Models for Generation of Audio Data Based on Descriptive Textual Prompts
    6.
    发明公开
    Diffusion Models for Generation of Audio Data Based on Descriptive Textual Prompts 审中-公开

    公开(公告)号：US20240282294A1

    公开(公告)日：2024-08-22

    申请号：US18651296

    申请日：2024-04-30

    Applicant: Google LLC

    Inventor： Qingqing Huang ,  Daniel Sung-Joon Park ,  Aren Jansen ,  Timo Immanuel Denk ,  Yue Li ,  Ravi Ganti ,  Dan Ellis ,  Tao Wang ,  Wei Han ,  Joonseok Lee

    IPC: G10L15/06 ,  G10L15/16

    CPC classification number: G10L15/063 ,  G10L15/16

    Abstract: A corpus of textual data is generated with a machine-learned text generation model. The corpus of textual data includes a plurality of sentences. Each sentence is descriptive of a type of audio. For each of a plurality of audio recordings, the audio recording is processed with a machine-learned audio classification model to obtain training data including the audio recording and one or more sentences of the plurality of sentences closest to the audio recording within a joint audio-text embedding space of the machine-learned audio classification model. The sentence(s) are processed with a machine-learned generation model to obtain an intermediate representation of the one or more sentences. The intermediate representation is processed with a machine-learned cascaded diffusion model to obtain audio data. The machine-learned cascaded diffusion model is trained based on a difference between the audio data and the audio recording.

    Audio-visual separation of on-screen sounds based on machine learning models
    9.
    发明授权
    Audio-visual separation of on-screen sounds based on machine learning models 有权

    公开(公告)号：US12217768B2

    公开(公告)日：2025-02-04

    申请号：US18226545

    申请日：2023-07-26

    Applicant: Google LLC

    Inventor： Efthymios Tzinis ,  Scott Wisdom ,  Aren Jansen ,  John R. Hershey

    IPC: G10L25/57 ,  G06F18/214 ,  G06N3/088 ,  G06V20/40 ,  G10L25/30

    Abstract: Apparatus and methods related to separation of audio sources are provided. The method includes receiving an audio waveform associated with a plurality of video frames. The method includes estimating, by a neural network, one or more audio sources associated with the plurality of video frames. The method includes generating, by the neural network, one or more audio embeddings corresponding to the one or more estimated audio sources. The method includes determining, based on the audio embeddings and a video embedding, whether one or more audio sources of the one or more estimated audio sources correspond to objects in the plurality of video frames. The method includes predicting, by the neural network and based on the one or more audio embeddings and the video embedding, a version of the audio waveform comprising audio sources that correspond to objects in the plurality of video frames.

Patent Agency Ranking