System and method for speaker identification in audio data

    公开(公告)号:US11373657B2

    公开(公告)日:2022-06-28

    申请号:US16864856

    申请日:2020-05-01

    摘要: A system for identifying audio data includes a feature extraction module receiving unknown input audio data and dividing the unknown input audio data into a plurality of segments of unknown input audio data. A similarity module receives the plurality of segments of the unknown input audio data and receives known audio data from a known source, the known audio data being divided into a plurality of segments of known audio data. The similarity module performs comparisons between the segments of unknown input audio data and respective segments of known audio data and generates a respective plurality of similarity values representative of similarity between the segments of the comparisons, the comparisons being performed serially. The similarity module terminates the comparisons if the similarity values indicate insufficient similarity between the segments of the comparisons, prior to completing comparisons for all segments of the unknown input audio data.

    Frequency selective system
    2.
    发明授权

    公开(公告)号:US10574374B2

    公开(公告)日:2020-02-25

    申请号:US15880242

    申请日:2018-01-25

    发明人: Michael Ready

    摘要: A frequency-selective system that may be used as, or as part of, an add/drop multiplexer. An input signal is fed to a Mach-Zehnder interferometer configured to drop, or suppress, by destructive interference, a signal component in a first frequency band from among a plurality of frequency bands. One or more bandpass filters in one arm of the Mach-Zehnder interferometer suppress other frequencies, outside of the first frequency band, so that signals at these other frequencies are not suppressed by destructive interference and are present at the output of the Mach-Zehnder interferometer. A coupler connected after the output of the Mach-Zehnder interferometer adds, into the signal path, a replacement for the dropped signal.

    System and method for determining geo location of a target using locus of emitter positions (LEP)
    3.
    发明授权
    System and method for determining geo location of a target using locus of emitter positions (LEP) 有权
    用于使用发射器位置(LEP)的轨迹确定目标的地理位置的系统和方法

    公开(公告)号:US09383429B2

    公开(公告)日:2016-07-05

    申请号:US13654155

    申请日:2012-10-17

    发明人: William May

    CPC分类号: G01S5/02 G01S5/12 G01S11/04

    摘要: A system and method for determining geo position of a target by an aircraft, including: (a). electronically receiving navigation data related to the aircraft and multilateration information related to the target; (b). electronically calculating a locus of emitter positions (LEP) curve from the received navigation data and multilateration information; (c). repeating steps (a) and (b), as the aircraft moves toward or away from the target; (d). electronically accumulating, in a computer storage medium, the calculated LEP curves; and (e). electronically determining a position that is closest to all the accumulated LEP curves to establish a position of the target.

    摘要翻译: 一种用于确定飞机的目标的地理位置的系统和方法,包括:(a)。 电子地接收与飞机相关的导航数据和与目标相关的多边信息; (b)。 从接收到的导航数据和多边信息电子地计算发射器位置(LEP)曲线的轨迹; (C)。 重复步骤(a)和(b),当飞机朝着或远离目标移动时; (d)。 在计算机存储介质中电累积所计算的LEP曲线; 和(e)。 电子地确定最接近所有累积的LEP曲线的位置以建立目标的位置。

    Systems and methods for fast filtering of audio keyword search

    公开(公告)号:US12020697B2

    公开(公告)日:2024-06-25

    申请号:US16929383

    申请日:2020-07-15

    摘要: An audio keyword searcher arranged to identify a voice segment of a received audio signal; identify, by an automatic speech recognition engine, one or more phonemes included in the voice segment; output, from the automatic speech recognition engine, the one or more phonemes to a keyword filter to detect whether the voice segment includes any of the one or more first keywords of the first keyword list and, if detected, output the one or more phonemes included in the voice segment to a decoder but, if not detected, not output the one or more phonemes included in the voice segment to the decoder. If the one or more phonemes are output to the decoder: generate a word lattice associated with the voice segment; search the word lattice for one or more second keywords, and determine whether the voice segment includes the one or more second keywords.

    OPEN DISTRIBUTED ASYNCHRONOUS DEPENDENCY-BASED CONTENT PROCESSING

    公开(公告)号:US20240036922A1

    公开(公告)日:2024-02-01

    申请号:US17878777

    申请日:2022-08-01

    发明人: Jonathan Wintrode

    IPC分类号: G06F9/48 G06F9/54

    CPC分类号: G06F9/4887 G06F9/546

    摘要: Method for distributed asynchronous dependency-based content processing includes: receiving a multi-media digital content and a task to be performed on the multi-media digital content; determining types of the multi-media digital content; generating a workflow graph for each type of the content, each workflow graph including data dependency conditions of the task; generating a task message for each workflow graph; broadcasting the task messages to a respective task queue of an initial state of a workflow manager; responding to the broadcast task messages by a respective processing node;
    processing the task based on the respective workflow graph in the broadcast task message, and including a result of the processing for each workflow graph in a result message; broadcasting the result messages by the respective processing node; accumulating the broadcast result messages responsive to respective workflow graphs; and outputting the accumulated results to a user or an external system.

    System and method for language identification in audio data

    公开(公告)号:US11282499B2

    公开(公告)日:2022-03-22

    申请号:US16924564

    申请日:2020-07-09

    IPC分类号: G10L15/00 G10L15/08 G10L25/78

    摘要: A system for identifying a language in audio data includes a feature extraction module for receiving an unknown input audio data stream and dividing the unknown input audio data stream into segments. A similarity module receives the segments and receives known-language audio data models for known languages. For each segment, the similarity module performs comparisons between the segment and the known-language audio data models and generates probability values representative of the probabilities that the segment includes audio data of the known languages. A processor receives the probability values for each segment and computes an entropy value for the probabilities for each segment. If the entropy value for a segment is less than the entropy value for a previous segment, the processor terminates the comparisons prior to completing comparisons for all segments.

    Smart receiver with compressive sensing and machine learning

    公开(公告)号:US10924308B1

    公开(公告)日:2021-02-16

    申请号:US16745204

    申请日:2020-01-16

    摘要: System and method for identifying an RF emitter include: channelizers for channelizing RF signals into several channels; a compressive sensing (CS) encoder for each channel to CS encode the channelized signal to produce an encoded channelized signal in each of the plurality of channels; a summer to sum the encoded channelized signals of all of the plurality of channels to produce an I/Q data; a channelized pulse detection circuit to detect pulses in each channel and produce encoded pulse snippets from the I/Q data; a CS decoder for each channel to CS decode the encoded pulse snippets; a first machine learning device to characterize the decoded pulse snippets and to produce pulse description words (PDWs); and a second machine learning device to associate the PDWs with one or more RF emitters and identify the one or more RF emitters.

    System and method for determining geo location of a target using a cone coordinate system

    公开(公告)号:US10670689B2

    公开(公告)日:2020-06-02

    申请号:US15673385

    申请日:2017-08-09

    发明人: William D. May

    摘要: A method for determining geo-position of a target by an aircraft includes: receiving navigation data related to the aircraft including aircraft attitude information; receiving multilateration information related to the target including an angle to the target; calculating an axis for a cone fixed to the aircraft, based on the received aircraft attitude information; calculating a central angle for the cone from the received angle to the target; generating two vectors orthogonal to the cone axis; calculating a cone model from the axis, the central angle and the two vectors; and intersecting the cone model with an earth model to obtain a LEP curve, wherein the LEP curve is used to determine the geo position of the target.