中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

45 records (took 0.032 seconds)

    Automatic speech recognition with filler model processing
    2.
    发明授权
    Automatic speech recognition with filler model processing 有权

    公开(公告)号：US11062703B2

    公开(公告)日：2021-07-13

    申请号：US16106852

    申请日：2018-08-21

    Applicant: Intel Corporation

    Inventor： Josef Bauer ,  Tobias Bocklet ,  Joachim Hofer ,  Munir Georges

    IPC: G10L15/22 ,  G10L15/02 ,  G10L25/54 ,  G10L17/04

    Abstract: An automatic speech recognition (ASR) system includes a memory configured to store a filler model. The filler model includes one or more phonetic strings corresponding to one or more portions of a wake up phrase. The ASR system also includes one or more processors operatively coupled to the memory and configured to analyze a speech signal with the filler model to determine whether the speech signal includes the wake up phrase or any portion of the wake up phrase. The one or more processors are also configured to generate, based on the analysis, a hypothesis of underlying speech included in the speech signal. The hypothesis excludes the wake up phrase or any portion of the wake up phrase included in the speech signal.

    Speech classification of audio for wake on voice
    4.
    发明授权
    Speech classification of audio for wake on voice 有权

    公开(公告)号：US10714122B2

    公开(公告)日：2020-07-14

    申请号：US16001496

    申请日：2018-06-06

    Applicant: Intel Corporation

    Inventor： Maciej Muchlinski ,  Tobias Bocklet

    IPC: G10L25/78 ,  G10L25/84 ,  G10L15/02 ,  G10L15/22 ,  G10L25/87 ,  G10L15/06 ,  G10L15/08 ,  G10L15/14 ,  G10L15/16

    Abstract: Speech or non-speech detection techniques are discussed and include updating a speech pattern model using probability scores from an acoustic model to generate a score for each state of the speech pattern model, such that the speech pattern model includes a first non-speech state having multiple self loops each associated with a non-speech probability score of the probability scores, a plurality of speech states following the first non-speech state, and a second non-speech state following the speech states, and detecting speech based on a comparison of a score of the first non-speech state and a score of the last speech state of the multiple speech states.

    TRAINING CLASSIFIERS USING SELECTED COHORT SAMPLE SUBSETS
    6.
    发明申请
    TRAINING CLASSIFIERS USING SELECTED COHORT SAMPLE SUBSETS 审中-公开
    使用选择的联合样本附件培训分类器

    公开(公告)号：US20160365096A1

    公开(公告)日：2016-12-15

    申请号：US15121004

    申请日：2014-03-28

    Applicant: INTEL CORPORATION

    Inventor： Tobias Bocklet ,  Adam Marek

    IPC: G10L17/04 ,  G10L17/16 ,  G10L17/08 ,  G10L17/02

    CPC classification number: G10L17/04 ,  G10L17/02 ,  G10L17/08 ,  G10L17/16

    Abstract: Various systems, apparatuses, and methods for training classifiers using selected cohort sample subsets are disclosed herein, in an example, a set of target supervectors, representing a target class, is received, and a set of cohort supervectors, representing a cohort class, is received. A distance metric is calculated from a respective cohort supervector to a respective target supervector, and a proper subset of cohort supervectors are selected based on the calculated distance metrics. The set of target supervectors and the selected proper subset of cohort supervectors are used to train a classifier. Further examples described herein describe how training classifiers using selected cohort sample subsets may be used to increase performance and decrease resource consumption in voice biometric systems.

    Abstract translation: 在本文中公开了使用所选择的队列样本子集来训练分类器的各种系统，装置和方法，在一个示例中，接收到表示目标类的一组目标超向量，并且代表队列类的一组队列超向量是 收到了 从相应的队列超向量到相应的目标超向量计算距离度量，并且基于所计算的距离度量来选择队列超级向量的适当子集。 目标超级队员和选定的队列超级队员的子集用于训练分类器。 本文描述的进一步示例描述如何使用选择的队列样本子集的训练分类器可以用于增加语音生物测定系统中的性能并降低资源消耗。

    Acoustic event detection based on modelling of sequence of event subparts
    8.
    发明授权
    Acoustic event detection based on modelling of sequence of event subparts 有权

    公开(公告)号：US11216724B2

    公开(公告)日：2022-01-04

    申请号：US15834838

    申请日：2017-12-07

    Applicant: INTEL CORPORATION

    Inventor： Kuba Lopatka ,  Tobias Bocklet ,  Mateusz Kotarski

    IPC: G06N3/08 ,  G06K9/62 ,  G06F16/683 ,  G10L25/51 ,  G06N20/10 ,  G10L25/18 ,  G06N3/04 ,  G06N7/00

    Abstract: Techniques are provided for acoustic event detection. A methodology implementing the techniques according to an embodiment includes extracting acoustic features from a received audio signal. The acoustic features may include, for example, one or more short-term Fourier transform frames, or other spectral energy characteristics, of the audio signal. The method also includes applying a trained classifier to the extracted acoustic features to identify and label acoustic event subparts of the audio signal and to generate scores associated with the subparts. The method further includes performing sequence decoding of the acoustic event subparts and associated scores to detect target acoustic events of interest based on the scores and temporal ordering sequence of the event subparts. The classifier is trained on acoustic event subparts that are generated through unsupervised subspace clustering techniques applied to training data that includes target acoustic events.

Patent Agency Ranking