利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

51 条记录 (耗时 0.014 秒)

    CEPSTRAL SEPARATION DIFFERENCE
    5.
    发明公开
    CEPSTRAL SEPARATION DIFFERENCE 审中-公开
    CEPSTRAL分离差异

    公开(公告)号：EP2862169A2

    公开(公告)日：2015-04-22

    申请号：EP13803604.1

    申请日：2013-06-05

    申请人： Jemardator AB

    发明人： KHAN, Taha ,  WESTIN, Jerker ,  DAUGHERTY, Mark

    IPC分类号： G10L25/66 ,  G10L25/24

    CPC分类号： G10L21/06 ,  G10L15/02 ,  G10L19/02 ,  G10L25/03 ,  G10L25/60 ,  G10L25/66

    摘要： A method for characterization of a human speech comprises performing (220) of a discrete transform on a speech sample of the human speech. A speech logarithmic power spectrum is created (222) by taking a logarithmic of the speech frequency spectrum. An inverse discrete transform is performed (224) on the speech logarithmic power spectrum into the quefrency domain. Lifterings (226, 228) of the speech cepstrum is performed, giving a high and low end speech cepstrum, respectively. The discrete transform is performed (230) on the high end speech cepstrum, creating a source excitation log-power spectrum. The discrete transform is performed (232) on the low end speech cepstrum, creating a vocal tract filter log-power spectrum. A cepstral separation difference is calculated (234) as a difference between the source excitation log-power spectrum and the vocal tract filter log-power spectrum. The human speech is characterized (238) based on the cepstral separation difference.

    摘要翻译： 用于表征人类语音的方法包括对人类语音的语音样本执行（220）离散变换。 通过取对数的语音频谱来创建（222）语音对数功率谱。 对语音对数功率谱进行逆离散变换（224）到逆频域。 执行语音倒谱的Lifterings（226,228），分别给出高端和低端语音倒谱。 对高端语音倒谱执行离散变换（230），产生源激励对数功率谱。 在低端语音倒谱上执行（232）离散变换，创建声道滤波器对数功率谱。 作为声源激励对数功率谱和声道滤波对数功率谱之差来计算（234）倒谱差分差。 基于倒谱分离差异来表征人类言语（238）。

    ACTIVE NOISE REDUCTION METHOD, DEVICE AND SYSTEM
    7.
    发明公开
    ACTIVE NOISE REDUCTION METHOD, DEVICE AND SYSTEM 审中-公开

    公开(公告)号：EP4254979A1

    公开(公告)日：2023-10-04

    申请号：EP21909336.6

    申请日：2021-12-20

    申请人： Huawei Technologies Co., Ltd.

    发明人： ZHANG, Libin ,  YUAN, Tingqiu ,  ZHANG, Huimin

    IPC分类号： H04R1/10 ,  G10L17/00 ,  G10L19/02 ,  G10L19/26 ,  G10L25/24 ,  G10K11/178

    摘要： An active noise cancellation method is provided. The method includes: capturing an ambient sound to determine an ambient audio signal; and determining a working status, determining at least one corresponding wanted signal based on the working status, and then removing the at least one wanted signal from the ambient audio signal, to obtain a reference signal, where the wanted signal includes content of interest. If the method is applied to a headset, a to-be-played signal is determined based on the reference signal, and the to-be-played signal is played, so that the reference signal is superimposed with the ambient sound, the at least one wanted signal is retained, and ambient noise is canceled. If the method is applied to a collaboration device, a to-be-played signal is determined based on the reference signal, and the to-be-played signal is sent to the headset. The content of interest is removed from the reference signal, to ensure that when active noise cancellation is performed, the content of interest is still retained in audio data obtained after noise cancellation.

    DEVICE WAKEUP METHOD AND APPARATUS, ELECTRONIC DEVICE, AND STORAGE MEDIUM
    8.
    发明公开
    DEVICE WAKEUP METHOD AND APPARATUS, ELECTRONIC DEVICE, AND STORAGE MEDIUM 审中-公开

    公开(公告)号：EP3923275A1

    公开(公告)日：2021-12-15

    申请号：EP21155304.5

    申请日：2021-02-04

    申请人： Beijing Xiaomi Pinecone Electronics Co., Ltd.

    发明人： WANG, Zhao

    IPC分类号： G10L15/22 ,  G10L15/30 ,  G10L25/24

    摘要： The present disclosure relates to a device wakeup method and apparatus, an electronic device, and a storage medium. The wakeup method is applied to a first electronic device and includes: a wakeup message from a second electronic device is received, and when determining that a present state is an unawakened state, locally collected voice data is acquired (S11); MFCC extraction is performed on the voice data to acquire a first MFCC of the voice data (S12); the wakeup message is parsed to obtain a second MFCC comprised in the wakeup message (S13); the first MFCC and the second MFCC are matched, and when determining that a difference between the first MFCC and the second MFCC is less than or equal to a set threshold value, a wakeup instruction is generated (S14); and responsive to the wakeup instruction, the first electronic device is woken up (S15).