利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

64 条记录 (耗时 0.026 秒)

    SPECTRAL REFINEMENT SYSTEM
    11.
    发明申请
    SPECTRAL REFINEMENT SYSTEM 有权
    光谱精制系统

    公开(公告)号：US20080195382A1

    公开(公告)日：2008-08-14

    申请号：US11948137

    申请日：2007-11-30

    申请人： Mohamed Krini ,  Gerhard Uwe Schmidt

    发明人： Mohamed Krini ,  Gerhard Uwe Schmidt

    IPC分类号： G10L19/02

    CPC分类号： G10L19/0204 ,  G10L21/02 ,  G10L25/18 ,  G10L25/27

    摘要： An audio enhancement refines a short-time spectrum. The refinement may reduce overlap between audio sub-bands. The sub-bands are transformed into sub-band short-time spectra. A portion of the spectra are time-delayed. The sub-band short-time spectrum and the time-delayed portion are filtered to obtain a refined sub-band short-time spectrum. The refined spectrum improves audio processing.

    摘要翻译： 音频增强优化了短时间频谱。 细化可以减少音频子带之间的重叠。 子带被转换成子带短时光谱。 光谱的一部分是时间延迟的。 子带短时频谱和时间延迟部分被滤波以获得精确的子带短时频谱。 精致的频谱改进了音频处理。

    MODEL-BASED SIGNAL ENHANCEMENT SYSTEM
    12.
    发明申请
    MODEL-BASED SIGNAL ENHANCEMENT SYSTEM 审中-公开
    基于模型的信号增强系统

    公开(公告)号：US20080140396A1

    公开(公告)日：2008-06-12

    申请号：US11928251

    申请日：2007-10-30

    申请人： Dominik Grosse-Schulte ,  Mohamed Krini ,  Gerhard Uwe Schmidt

    发明人： Dominik Grosse-Schulte ,  Mohamed Krini ,  Gerhard Uwe Schmidt

    IPC分类号： G10L21/02

    CPC分类号： G10L15/20 ,  G10L21/0208 ,  G10L21/0264

    摘要： A signal processing system enhances a speech input signal. A signal reconstruction circuit receives the speech input signal and extracts a spectral envelope. The signal reconstruction circuit generates an excitation signal based on the input signal, and generates a reconstructed speech signal based on the extracted spectral envelope and an excitation signal. A combining circuit combines the noise reduced signal and the reconstructed speech signal. Signal reconstruction and signal combinations may be based on a signal-to-noise ratio of the speech signal or another input.

    摘要翻译： 信号处理系统增强语音输入信号。 信号重构电路接收语音输入信号并提取频谱包络。 信号重建电路基于输入信号产生激励信号，并且基于所提取的频谱包络和激励信号产生重构的语音信号。 组合电路组合了降噪信号和重构语音信号。 信号重建和信号组合可以基于语音信号或另一输入的信噪比。

    Adjusting or setting vehicle elements through speech control
    13.
    发明授权
    Adjusting or setting vehicle elements through speech control 有权
    通过语音控制调整或设置车辆元件

    公开(公告)号：US09580028B2

    公开(公告)日：2017-02-28

    申请号：US12241837

    申请日：2008-09-30

    申请人： Markus Buck ,  Tim Haulick ,  Gerhard Uwe Schmidt

    发明人： Markus Buck ,  Tim Haulick ,  Gerhard Uwe Schmidt

    IPC分类号： G10L15/22 ,  B60R16/037 ,  G10L15/26 ,  G10L17/00

    CPC分类号： B60R16/0373 ,  G10L15/22 ,  G10L15/265 ,  G10L17/005

    摘要： A speech processing device includes an automotive device that filters data that is sent and received across an in-vehicle bus. The device selectively acquires vehicle data related to a user settings or adjustments. An interface acquires the selected vehicle data from in-vehicle sensors in response to a user's articulation of a first code phrase. A memory stores the selected vehicle data with unique identifying data associated with the user and establishes a connection between the selected vehicle data and the user when a second code phrase is articulated. A data interface provides access to the selected vehicle data and stored relationship data and enables the processing of the data to customize the in-vehicle system. The data interface is responsive to the user's articulation of a third code phrase to process the selected vehicle data that enables the setting or adjustment of the in-vehicle system.

    摘要翻译： 语音处理装置包括：汽车装置，其对通过车载总线发送和接收的数据进行滤波。 该设备选择性地获取与用户设置或调整相关的车辆数据。 响应于用户对第一代码短语的表达，接口从车载传感器中获取所选择的车辆数据。 存储器使用与用户相关联的唯一识别数据存储所选择的车辆数据，并且当第二代码短语被铰接时，建立所选择的车辆数据与用户之间的连接。 数据接口提供对所选择的车辆数据和存储的关系数据的访问，并使数据的处理能够定制车载系统。 数据接口响应于用户对第三代码短语的表达，以处理能够设置或调整车载系统的所选车辆数据。

    Multi-channel echo compensation system
    15.
    发明授权
    Multi-channel echo compensation system 有权
    多通道回波补偿系统

    公开(公告)号：US08130969B2

    公开(公告)日：2012-03-06

    申请号：US11787348

    申请日：2007-04-16

    申请人： Markus Buck ,  Tim Haulick ,  Martin Roessler ,  Gerhard Uwe Schmidt

    发明人： Markus Buck ,  Tim Haulick ,  Martin Roessler ,  Gerhard Uwe Schmidt

    IPC分类号： H04B3/20 ,  H04B15/00

    CPC分类号： H04M9/082 ,  H04R3/02 ,  H04R2499/13

    摘要： An echo compensation system may remove undesirable audio signals. The echo compensation system may utilize adaptive filters to remove echoes and undesirable signals received by a microphone. The echo compensation system may inhibit adaptation of an adaptive filter when left and right channel audio signals are highly correlated. In a two-channel system, inhibiting adaptation of one of two adaptive filters may reduce computational power requirements, while still removing undesirable signals. In a four-channel system, inhibiting adaptation of all but one of the four adaptive filters may reduce computational power requirements by a greater percentage.

    摘要翻译： 回波补偿系统可以去除不需要的音频信号。 回波补偿系统可以利用自适应滤波器去除由麦克风接收的回波和不期望的信号。 当左右声道音频信号高度相关时，回波补偿系统可以抑制自适应滤波器的自适应。 在双通道系统中，禁止两个自适应滤波器之一的适配可以减少计算能力需求，同时仍然消除不需要的信号。 在四通道系统中，禁止四个自适应滤波器中除了一个之外的所有适配器可以将计算能力要求降低更多的百分比。

    SYSTEM FOR SPEECH SIGNAL ENHANCEMENT IN A NOISY ENVIRONMENT THROUGH CORRECTIVE ADJUSTMENT OF SPECTRAL NOISE POWER DENSITY ESTIMATIONS
    16.
    发明申请
    SYSTEM FOR SPEECH SIGNAL ENHANCEMENT IN A NOISY ENVIRONMENT THROUGH CORRECTIVE ADJUSTMENT OF SPECTRAL NOISE POWER DENSITY ESTIMATIONS 有权
    通过光谱噪声功率密度估计的正确调整，噪声环境中的语音信号增强系统

    公开(公告)号：US20090063143A1

    公开(公告)日：2009-03-05

    申请号：US12202147

    申请日：2008-08-29

    申请人： Gerhard Uwe Schmidt ,  Tobias Wolff ,  Markus Buck

    发明人： Gerhard Uwe Schmidt ,  Tobias Wolff ,  Markus Buck

    IPC分类号： G10L15/20

    CPC分类号： H04R3/00 ,  G10L21/0208 ,  G10L21/0216

    摘要： A system estimates the spectral noise power density of an audio signal includes a spectral noise power density estimation unit, a correction term processor, and a combination processor. The spectral noise power density estimation unit may provide a first estimate of the spectral noise power density of the audio signal. The correction term processor may provide a time dependent correction term based, at least in part, on a spectral noise power density estimation error of the actual spectral noise power density. The correction term may be determined so that the spectral noise power density estimation error is reduced. The combination processor may combine the first estimate with the correction term to obtain a second estimate of the spectral noise power density that may be used for subsequent signal processing to enhance a desired signal component of the audio signal.

    摘要翻译： 系统估计音频信号的频谱噪声功率密度包括频谱噪声功率密度估计单元，校正项处理器和组合处理器。 频谱噪声功率密度估计单元可以提供音频信号的频谱噪声功率密度的第一估计。 校正项处理器可以至少部分地基于实际频谱噪声功率密度的频谱噪声功率密度估计误差来提供时间相关校正项。 可以确定校正项，使得谱噪声功率密度估计误差降低。 组合处理器可以将第一估计与校正项组合以获得可用于后续信号处理以增强音频信号的期望信号分量的频谱噪声功率密度的第二估计。

    DETECTING BARGE-IN IN A SPEECH DIALOGUE SYSTEM
    20.
    发明申请
    DETECTING BARGE-IN IN A SPEECH DIALOGUE SYSTEM 有权
    检测语音对话系统中的边界

    公开(公告)号：US20090254342A1

    公开(公告)日：2009-10-08

    申请号：US12415927

    申请日：2009-03-31

    申请人： Markus Buck ,  Franz Gerl ,  Tim Haulick ,  Tobias Herbig ,  Gerhard Uwe Schmidt ,  Matthias Schulz

    发明人： Markus Buck ,  Franz Gerl ,  Tim Haulick ,  Tobias Herbig ,  Gerhard Uwe Schmidt ,  Matthias Schulz

    IPC分类号： G10L17/00 ,  G10L15/20

    CPC分类号： G10L25/78 ,  G10L15/222 ,  G10L17/00 ,  G10L2025/786

    摘要： A method for detecting barge-in in a speech dialogue system comprising determining whether a speech prompt is output by the speech dialogue system, and detecting whether speech activity is present in an input signal based on a time-varying sensitivity threshold of a speech activity detector and/or based on speaker information, where the sensitivity threshold is increased if output of a speech prompt is determined and decreased if no output of a speech prompt is determined. If speech activity is detected in the input signal, the speech prompt may be interrupted or faded out. A speech dialogue system configured to detect barge-in is also disclosed.

    摘要翻译： 一种用于检测语音对话系统中的插入的方法，包括确定语音对话系统是否输出语音提示，以及基于语音活动检测器的时变灵敏度阈值来检测语音活动是否存在于输入信号中 和/或基于说话者信息，其中如果确定了语音提示的输出，则在不确定语音提示的输出的情况下确定并减小了灵敏度阈值。 如果在输入信号中检测到语音活动，语音提示可能被中断或淡出。 还公开了一种配置成检测插入的语音对话系统。