利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

25 条记录 (耗时 0.016 秒)

    AUDIO-BASED DETECTION AND TRACKING OF EMERGENCY VEHICLES
    1.
    发明申请
    AUDIO-BASED DETECTION AND TRACKING OF EMERGENCY VEHICLES 审中-公开

    公开(公告)号：US20200213728A1

    公开(公告)日：2020-07-02

    申请号：US16814361

    申请日：2020-03-10

    申请人： Intel Corporation

    发明人： Kuba Lopatka ,  Adam Kupryjanow ,  Lukasz Kurylo ,  Karol Duzinkiewicz ,  Przemyslaw Maziewski ,  Marek Zabkiewicz

    IPC分类号： H04R3/00 ,  H04R1/40 ,  G10L25/51 ,  G10L25/30 ,  G10L25/18 ,  H04R3/04 ,  G10L21/0232 ,  G06N3/08

    摘要： Techniques are provided for audio-based detection and tracking of an acoustic source. A methodology implementing the techniques according to an embodiment includes generating acoustic signal spectra from signals provided by a microphone array, and performing beamforming on the acoustic signal spectra to generate beam signal spectra, using time-frequency masks to reduce noise. The method also includes detecting, by a deep neural network (DNN) classifier, an acoustic event, associated with the acoustic source, in the beam signal spectra. The DNN is trained on acoustic features associated with the acoustic event. The method further includes performing pattern extraction, in response to the detection, to identify time-frequency bins of the acoustic signal spectra that are associated with the acoustic event, and estimating a motion direction of the source relative to the array of microphones based on Doppler frequency shift of the acoustic event calculated from the time-frequency bins of the extracted pattern.

    SPEECH RECOGNITION WITH BRAIN-COMPUTER INTERFACES
    4.
    发明申请
    SPEECH RECOGNITION WITH BRAIN-COMPUTER INTERFACES 有权

    公开(公告)号：US20210104244A1

    公开(公告)日：2021-04-08

    申请号：US17121444

    申请日：2020-12-14

    申请人： Intel Corporation

    发明人： Przemyslaw Maziewski

    IPC分类号： G10L15/26 ,  H04R1/46 ,  G10L15/06 ,  G10L15/24

    摘要： In an embodiment, a system includes a first sensor sensing brain signal data from a user, the brain signal data including nerve signals transmitted via a brain of the user and corresponding to a first set of words spoken by the user. The system also includes a second sensor sensing audio data from the user corresponding to the first set of words and one or more processors communicatively coupled to the first sensor and the second sensor. In the embodiment, the one or more processors generate text data based on the audio data using a machine learning algorithm and re-train the machine learning algorithm based on the brain signal data and the text data to generate a re-trained machine learning algorithm, wherein the re-trained machine learning algorithm generates second text data associated with a second set of words based on second brain signal data.

    ENVIRONMENT CLASSIFIER FOR DETECTION OF LASER-BASED AUDIO INJECTION ATTACKS
    5.
    发明申请
    ENVIRONMENT CLASSIFIER FOR DETECTION OF LASER-BASED AUDIO INJECTION ATTACKS 审中-公开

    公开(公告)号：US20200243067A1

    公开(公告)日：2020-07-30

    申请号：US16849525

    申请日：2020-04-15

    申请人： Intel Corporation

    发明人： Przemyslaw Maziewski ,  Jan Banas ,  Piotr Klinke ,  Damian Koszewski ,  Pawel Pach ,  Dominik Stanczak ,  Pawel Trella

    IPC分类号： G10L15/02 ,  G10L15/04

    摘要： Techniques are provided for detection of laser-based audio injection attacks through classification of the acoustic environment. A methodology implementing the techniques according to an embodiment includes broadcasting a reference signal over a loudspeaker into a local environment, and generating a reference model of the local environment based on analysis of a transformed version of that reference signal received through a microphone of the device. The method further includes generating an estimate model based on analysis of a segment of speech in an audio signal received through the microphone. The estimate model is associated with an environment in which the speech was generated. The method further includes calculating a similarity metric (e.g., mathematical distance) between the reference model and the estimate model, and providing warning of a laser-based audio attack if the similarity metric exceeds a threshold value associated with an attack.

    Simultaneous multi-user audio signal recognition and processing for far field audio
    6.
    发明授权
    Simultaneous multi-user audio signal recognition and processing for far field audio 有权

    公开(公告)号：US10438588B2

    公开(公告)日：2019-10-08

    申请号：US15702490

    申请日：2017-09-12

    申请人： Intel Corporation

    发明人： Raghavendra Rao R ,  Przemyslaw Maziewski ,  Adam Kupryjanow ,  Lukasz Kurylo

    IPC分类号： G10L15/20 ,  G10L15/22 ,  G10L17/00 ,  G10L15/08 ,  G10L21/0272 ,  H04R1/40 ,  G10L21/0216

    摘要： A mechanism is described for facilitating simultaneous recognition and processing of multiple speeches from multiple users according to one embodiment. A method of embodiments, as described herein, includes facilitating a first microphone to detect a first speech from a first speaker, and a second microphone to detect a second speech from a second speaker. The method may further include facilitating a first beam-former to receive and process the first speech, and a second beam-former to receive and process the second speech, where the first and second speeches are at least received or processed simultaneously. The method may further include communicating a first output associated with the first speech and a second output associated with the second speech to the first speaker and the second speaker, respectively, using at least one of one or more speaker devices and one or more display devices.

    Detection of laser-based audio injection attacks using channel cross correlation
    7.
    发明授权
    Detection of laser-based audio injection attacks using channel cross correlation 有权

    公开(公告)号：US11961535B2

    公开(公告)日：2024-04-16

    申请号：US16941191

    申请日：2020-07-28

    申请人： Intel Corporation

    发明人： Pawel Trella ,  Przemyslaw Maziewski ,  Jan Banas

    IPC分类号： G10L25/69 ,  G10L15/22 ,  H04R3/00

    CPC分类号： G10L25/69 ,  G10L15/22 ,  G10L2015/221 ,  H04R3/005

    摘要： Techniques are provided for detection of laser-based audio injection attacks. A methodology implementing the techniques according to an embodiment includes calculating cross correlations between signals received from microphones of an array of two or more microphones. The method also includes identifying time delays associated with peaks of the cross correlations, and magnitudes associated with the peaks of the cross correlations. The method further includes calculating a time alignment metric based on the time delays and calculating a similarity metric based on the magnitudes. The method further includes generating a first attack indicator based on a comparison of the time alignment metric to a first threshold and generating a second attack indicator based on a comparison of the similarity metric to a second threshold. The method further includes providing warning of a laser-based audio attack based on the first attack indicator and/or the second attack indicator.

    Ultrasonic attack prevention for speech enabled devices
    10.
    发明授权
    Ultrasonic attack prevention for speech enabled devices 有权

    公开(公告)号：US10565978B2

    公开(公告)日：2020-02-18

    申请号：US16118719

    申请日：2018-08-31

    申请人： INTEL CORPORATION

    发明人： Przemyslaw Maziewski ,  Jan Banas ,  Piotr Klinke ,  Pawel Pach ,  Jedrzej Prysko ,  Roksana Sokolowska-Kostyk ,  Dominik Stanczak ,  Pawel Trella

    IPC分类号： G10K11/178 ,  H04R3/00 ,  G10L21/0208

    摘要： Techniques are provided for defending against an ultrasonic attack on a speech enabled device. A methodology implementing the techniques according to an embodiment includes detecting voice activity in an audio signal received by the device and generating an ultrasonic jamming signal in response to the detection. The jamming signal is broadcast over a loudspeaker for up to the duration of the detected voice activity to defend against the ultrasonic attack. According to another embodiment, the ultrasonic jamming signal is generated in response to detection of a wake-on-voice key phrase in the received audio signal, and the jamming signal is broadcast over the loudspeaker for a time duration selected to be less than or equal to a time window during which spoken commands are accepted by the device following the wake-on-voice key phrase detection. The jamming signal may include white or colored noise, combinations of tones, and/or a periodic sweep frequency.