中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

114 records (took 0.017 seconds)

    NEURAL NETWORK BASED BLIND SOURCE SEPARATION
    2.
    发明申请
    NEURAL NETWORK BASED BLIND SOURCE SEPARATION 审中-公开

    公开(公告)号：WO2019094562A1

    公开(公告)日：2019-05-16

    申请号：PCT/US2018/059785

    申请日：2018-11-08

    Applicant: GOOGLE LLC

    Inventor： YAN, Longfei ,  KLEIJN, Willem Bastiaan

    IPC: G10L21/0272 ,  G10L25/30

    CPC classification number: G10L21/0272 ,  G10L25/30

    Abstract: A device includes a sound acquisition manager configured to receive a mixed audio signal including a first plurality of audio signals, an independent component analysis manager configured to determine a set of parameters configured to generate a second plurality of audio signals based on the first plurality of audio signals, and to minimize a correlation between pairs of signals of the converted second plurality of audio signals, and a memory configured to store the second plurality of audio signals as multi-channel audio data.

    생성적 대립 망 기반의 음성 대역폭 확장기 및 확장 방법
    3.
    发明申请
    생성적 대립 망 기반의 음성 대역폭 확장기 및 확장 방법 审中-公开

    公开(公告)号：WO2019004592A1

    公开(公告)日：2019-01-03

    申请号：PCT/KR2018/005647

    申请日：2018-05-17

    Applicant: 한양대학교 산학협력단

    Inventor： 장준혁 ,  노경진

    IPC: G10L19/038 ,  G10L25/30 ,  G10L21/038

    CPC classification number: G10L19/038 ,  G10L21/038 ,  G10L25/30

    Abstract: 생성적 대립 망 기반의 음성 대역폭 확장기 및 확장 방법이 제시된다.　일 실시예에 따른 생성적 대립 망 기반의 음성 대역폭 확장 방법은, 음성의 협대역(Narrowband, NB) 신호와 광대역(Wideband, WB) 신호에서 특징벡터를 추출하는 단계; 상기 협대역 신호의 특징벡터로부터 광대역 신호의 특징벡터를 추정하는 단계; 및 추출된 실제 상기 광대역 신호의 특징벡터와 상기 협대역 신호의 특징벡터로부터 추정된 광대역 신호의 특징벡터를 판별하는 심화 신경망 분류 모델을 학습시키는 단계를 포함하여 이루어질 수 있다.

    SYSTEMS AND METHODS FOR PREDICTING PRONUNCIATIONS WITH WORD STRESS
    5.
    发明申请
    SYSTEMS AND METHODS FOR PREDICTING PRONUNCIATIONS WITH WORD STRESS 审中-公开
    用词应力预测语音的系统和方法

    公开(公告)号：WO2017213696A1

    公开(公告)日：2017-12-14

    申请号：PCT/US2016/065759

    申请日：2016-12-09

    Applicant: GOOGLE LLC

    Inventor： CHUA, Mason Vijay ,  RAO, Kanury Kanishka ,  VAN ESCH, Daniel Jacobus Josef

    IPC: G10L13/10 ,  G10L25/30 ,  G10L15/187

    CPC classification number: G10L13/10 ,  G10L13/0335 ,  G10L13/047 ,  G10L13/08 ,  G10L15/02 ,  G10L15/063 ,  G10L15/16 ,  G10L15/1815 ,  G10L15/187 ,  G10L17/18 ,  G10L25/30 ,  G10L2015/027

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating word pronunciations. One of the methods includes determining, by one or more computers, spelling data that indicates the spelling of a word, providing the spelling data as input to a trained recurrent neural network, the trained recurrent neural network being trained to indicate characteristics of word pronunciations based at least on data indicating the spelling of words, receiving output indicating a stress pattern for pronunciation of the word generated by the trained recurrent neural network in response to providing the spelling data as input, using the output of the trained recurrent neural network to generate pronunciation data indicating the stress pattern for a pronunciation of the word, and providing, by the one or more computers, the pronunciation data to a text-to-speech system or an automatic speech recognition system.

    Abstract translation: 包括在计算机存储介质上编码的计算机程序的方法，系统和装置，用于生成单词发音。 其中一种方法包括由一个或多个计算机确定指示单词拼写的拼写数据，将拼写数据作为输入提供给训练的递归神经网络，训练后的递归神经网络被训练以指示基于单词发音的特征 至少在指示单词拼写的数据上，接收指示由训练的回归神经网络响应于提供拼写数据作为输入而生成的单词的发音的压力模式的输出，使用训练的回归神经网络的输出来生成发音 指示单词发音的压力模式的数据，以及通过一个或多个计算机将发音数据提供给文本到语音系统或自动语音识别系统。

    MULTI-SPEAKER SPEECH SEPARATION
    6.
    发明申请
    MULTI-SPEAKER SPEECH SEPARATION 审中-公开
    多音箱语音分离

    公开(公告)号：WO2017112466A1

    公开(公告)日：2017-06-29

    申请号：PCT/US2016/066430

    申请日：2016-12-14

    Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

    Inventor： YU, Dong

    IPC: G10L15/16 ,  G06N3/04 ,  G10L15/07 ,  G10L21/0272 ,  G10L17/18

    CPC classification number: G10L25/30 ,  G06N3/0445 ,  G10L15/07 ,  G10L15/16 ,  G10L15/197 ,  G10L15/20 ,  G10L15/22 ,  G10L15/26 ,  G10L17/18 ,  G10L21/0272 ,  G10L25/18 ,  G10L25/21 ,  G10L2015/223

    Abstract: The technology described herein uses a multiple-output layer RNN to process an acoustic signal comprising speech from multiple speakers to trace an individual speaker's speech. The multiple-output layer RNN has multiple output layers, each of which is meant to trace one speaker (or noise) and represent the mask for that speaker (or noise). The output layer for each speaker (or noise) can have the same dimensions and can be normalized for each output unit across all output layers. The rest of the layers in the multiple-output layer RNN are shared across all the output layers. The result from the previous frame is used as input to the output layer or to one of the hidden layers of the RNN to calculate results for the current frame. This pass back of results allows the model to carry information from previous frames to future frames to trace the same speaker.

    Abstract translation: 这里描述的技术使用多输出层RNN来处理包括来自多个扬声器的语音的声学信号以跟踪个体说话者的语音。 多输出层RNN具有多个输出层，每个输出层意味着跟踪一个扬声器（或噪声）并表示该扬声器（或噪声）的掩模。 每个扬声器（或噪声）的输出层可以具有相同的尺寸，并且可以针对所有输出层中的每个输出单元进行归一化。 多输出层RNN中的其余层在所有输出层之间共享。 来自前一帧的结果被用作输出层或RNN的隐藏层之一的输入，以计算当前帧的结果。 这种回传结果允许模型将来自先前帧的信息携带到未来帧以跟踪相同的说话者。

    一种语音质量评估方法、装置及设备
    7.
    发明申请
    一种语音质量评估方法、装置及设备 审中-公开

    公开(公告)号：WO2017092216A1

    公开(公告)日：2017-06-08

    申请号：PCT/CN2016/079528

    申请日：2016-04-18

    Applicant: 华为技术有限公司

    Inventor： 肖玮 ,  李素华 ,  杨付正

    IPC: G10L25/60

    CPC classification number: G10L25/60 ,  G10L25/18 ,  G10L25/21 ,  G10L25/30

    Abstract: 一种语音质量评估方法，包括：获取语音信号的时域包络（101）；对时域包络进行时频变换得到包络频谱（102）；对包络频谱进行特征提取获得特征参数（103）；根据特征参数进行通信语音质量评价获得语音信号的第一语音质量参数（104），通过网络参数评估模型计算语音信号的第二语音质量参数（105）；根据第一语音质量参数与第二语音质量参数进行综合分析得到该段输入的语音信号的质量评估参数（106）。一种语音质量评估装置以及语音质量评估设备。

    DEVICE IMPAIRMENT DETECTION
    8.
    发明申请
    DEVICE IMPAIRMENT DETECTION 审中-公开
    器件损害检测

    公开(公告)号：WO2017049164A1

    公开(公告)日：2017-03-23

    申请号：PCT/US2016/052258

    申请日：2016-09-16

    Applicant: SONOS, INC.

    Inventor： HARTUNG, Klaus ,  BRIGHT, Greg

    IPC: H04R3/04 ,  H04S7/00 ,  G06N3/02

    CPC classification number: G10L25/30 ,  G06F3/16 ,  G06N3/02 ,  G06N3/084 ,  H04R3/04 ,  H04R27/00 ,  H04R29/007 ,  H04R2227/005 ,  H04S7/301

    Abstract: Examples described herein involve detecting known impairments or other known conditions using a neural network. An example implementation involves receiving data indicating a response of a playback device as captured by a microphone. The implementation also involves determining an input vector by projecting a response vector that represents the response of the playback device onto a principle component matrix representing variance caused by one or more known impairments. The implementation further involves providing the determined input vector to a neural network that includes an output layer comprising neurons that correspond to respective known impairments. The implementation involves detecting that the input vector caused one or more neurons of the neural network to fire such that the neural network indicates that a particular known impairment is affecting the microphone and/or the playback device and adjusting operation of the playback device and/or the microphone to offset the particular known impairment.

    Abstract translation: 本文描述的示例涉及使用神经网络来检测已知的损伤或其他已知的条件。 示例实现涉及接收指示由麦克风捕获的播放设备的响应的数据。 该实现还包括通过将表示回放设备的响应的响应向量投影到表示由一个或多个已知损伤引起的方差的原理分量矩阵上来确定输入向量。 该实现还包括将确定的输入向量提供给神经网络，该神经网络包括包括对应于各自已知损伤的神经元的输出层。 该实现涉及检测输入向量导致神经网络的一个或多个神经元触发，使得神经网络指示特定的已知损伤影响麦克风和/或播放设备并且调整播放设备的操作和/或 麦克风抵消特定的已知损伤。

Patent Agency Ranking