Patents by Inventor Yangfei XU

Yangfei XU has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20240046955
    Abstract: A voice extraction method and apparatus (500), and an electronic device. The method comprises: acquiring microphone array data (303) (201, 401); performing signal processing on the microphone array data (303) to obtain a normalized feature (304) (202, 402), wherein the normalized feature (304) is used for representing the probability of a voice being present in a predetermined direction; on the basis of the microphone array data (303), determining a voice feature (306) of a voice in a target direction (203); and fusing the normalized feature (304) with the voice feature (306) of the voice in the target direction, and extracting voice data (309) in the target direction according to the voice feature (307) after same is subjected to fusion (204). Environmental noise is reduced, and the accuracy of extracted voice data is improved.
    Type: Application
    Filed: December 6, 2021
    Publication date: February 8, 2024
    Inventor: Yangfei XU
  • Publication number: 20240038252
    Abstract: A sound signal processing method, an electronic device, and computer-readable medium are provided. The method includes: importing first frequency spectrum data corresponding to first audio data into a pre-trained sound processing model to obtain a processing result; and generating, based on the processing result, pure audio data corresponding to the first audio data. The sound processing model includes at least one preset convolution layer, and operations performed by using the preset convolution layer includes: performing, based on a first convolution kernel group, a convolution operation on a first sound spectrum feature map inputted into the preset convolution layer, to obtain a second sound spectrum feature map; and combining, based on a second convolution kernel group, the obtained second sound spectrum feature map, to obtain a third sound spectrum feature map corresponding to the second convolution kernel group.
    Type: Application
    Filed: December 3, 2021
    Publication date: February 1, 2024
    Inventors: Wenzhi FAN, Fanliu KONG, Yangfei XU, Zhifei ZHANG
  • Patent number: 11804235
    Abstract: A double-talk state detection method includes: calculating an energy ratio between a first energy of an error signal in each sub-band of M sub-bands and a second energy of a filtered signal in the same sub-band as the error signal, thereby obtaining M energy ratios, where the error signal is a difference between an input signal collected by a microphone and the filtered signal, the filtered signal is a signal obtained after performing filtering process on a reference signal, and M is a positive integer; performing a first smoothing processing on the M energy ratios to obtain M first energy smoothing ratios, and performing a second smoothing processing on the M first energy smoothing ratios to obtain M second energy smoothing ratios; performing double-talk state detection based on the M first energy smoothing ratios and the M second energy smoothing ratios to determine a state of the input signal.
    Type: Grant
    Filed: February 5, 2021
    Date of Patent: October 31, 2023
    Assignee: Baidu Online Network Technology (Beijing) Co., Ltd.
    Inventors: Junnan Wu, Yangfei Xu, Jun Ning, Yuzhou Gong, Nan Zhou
  • Publication number: 20210264935
    Abstract: A double-talk state detection method includes: calculating an energy ratio between a first energy of an error signal in each sub-band of M sub-bands and a second energy of a filtered signal in the same sub-band as the error signal, thereby obtaining M energy ratios, where the error signal is a difference between an input signal collected by a microphone and the filtered signal, the filtered signal is a signal obtained after performing filtering process on a reference signal, and M is a positive integer; performing a first smoothing processing on the M energy ratios to obtain M first energy smoothing ratios, and performing a second smoothing processing on the M first energy smoothing ratios to obtain M second energy smoothing ratios; performing double-talk state detection based on the M first energy smoothing ratios and the M second energy smoothing ratios to determine a state of the input signal.
    Type: Application
    Filed: February 5, 2021
    Publication date: August 26, 2021
    Applicant: Baidu Online Network Technology (Beijing) Co., Ltd.
    Inventors: Junnan Wu, Yangfei Xu, Jun Ning, Yuzhou Gong, Nan Zhou
  • Patent number: 10685647
    Abstract: A speech recognition method and a speech recognition device are disclosed. The speech recognition method includes: obtaining features of a speech signal to be recognized; performing a path search in a search space generated by establishing a map according to the features to output a decoding result; judging whether a rejection is needed according to the decoding result; and when the rejection is needed, determining that a speech recognition result is the rejection, and when the rejection is not needed, obtaining the speech recognition result according to the decoding result. The method has a good recognition rejection effect.
    Type: Grant
    Filed: June 24, 2016
    Date of Patent: June 16, 2020
    Assignee: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.
    Inventors: Bin Yuan, Shouye Peng, Yangfei Xu
  • Publication number: 20180374478
    Abstract: A speech recognition method and a speech recognition device are disclosed. The speech recognition method includes: obtaining features of a speech signal to be recognized; performing a path search in a search space generated by establishing a map according to the features to output a decoding result; judging whether a rejection is needed according to the decoding result; and when the rejection is needed, determining that a speech recognition result is the rejection, and when the rejection is not needed, obtaining the speech recognition result according to the decoding result. The method has a good recognition rejection effect.
    Type: Application
    Filed: June 24, 2016
    Publication date: December 27, 2018
    Inventors: Bin YUAN, Shouye PENG, Yangfei XU