公开(公告)号：US20230402052A1

公开(公告)日：2023-12-14

申请号：US18248057

申请日：2021-10-08

申请人： EVOCO LABS CO., LTD.

发明人： Congxi LU ,  Linkai LI ,  Yufan YUAN ,  Hongcheng SUN

IPC分类号： G10L21/04 ,  G10L25/45

CPC分类号： G10L21/04 ,  G10L25/45

摘要： An audio signal processing method is disclosed. The method comprises: providing an input audio signal comprising a plurality of input data frames offset from each other by a predetermined frame shift and each input data frame having a predetermined frame length; performing first windowing process on the plurality of input data frames in sequence with a first window function; performing predetermined signal processing on the input audio signal after the first windowing processing, and generating an output audio signal; wherein the output audio signal has a plurality of output data frames each having the predetermined frame length corresponding to the plurality of input data frames of the input audio signal; performing second windowing processing on the plurality of output data frames in sequence with a second window function; and outputting the plurality of output data frames after the second windowing processing by superimposing the plurality of output data frames with the predetermined frame shift.

公开(公告)号：US20210074266A1

公开(公告)日：2021-03-11

申请号：US16930337

申请日：2020-07-16

申请人： EVOCO LABS CO., LTD.

发明人： Congxi LU ,  Linkai LI ,  Hongcheng SUN ,  Xinke LIU

IPC分类号： G10L15/06 ,  G06N3/04 ,  G10L15/16 ,  G10L19/005 ,  G06F17/14 ,  G10L19/083 ,  G06N3/08

摘要： A deep neural network based audio processing method is provided. The method includes: obtaining a deep neural network based speech extraction model; receiving an audio input object having a speech portion and a non-speech portion, wherein the audio input object includes one or more audio data frames each having a set of audio data samples sampled at a predetermined sampling interval and represented in time domain data format; obtaining a user audiogram and a set of user gain compensation coefficients associated with the user audiogram; and inputting the audio input object and the set of user gain compensation coefficients into the trained speech extraction model to obtain an audio output result represented in time domain data format outputted by the trained speech extraction model, wherein the non-speech portion of the audio input object is at least partially attenuated in or removed from the audio output result.

公开(公告)号：US20240265722A1

公开(公告)日：2024-08-08

申请号：US18566107

申请日：2022-05-23

申请人： EVOCO LABS CO., LTD.

发明人： Haoshuai ZHOU ,  Congxi LU ,  Linkai LI ,  Yufan YUAN ,  Hongcheng SUN

IPC分类号： G06V30/42 ,  G06V10/24 ,  G06V10/766 ,  G06V10/82 ,  G06V30/416

CPC分类号： G06V30/42 ,  G06V10/242 ,  G06V10/766 ,  G06V10/82 ,  G06V30/416

摘要： A method for identifying a chart comprises: acquiring an object image containing the chart, wherein the chart comprises a labeled area defined by a first coordinate axis and a second coordinate axis that intersect with each other, first coordinate labels along the first coordinate axis, second coordinate labels along the second coordinate axis, and a plurality of characteristic labels within the labeled area; processing the object image with a trained neural network to identify and separate the chart from the object image; processing the chart with a trained neural network to identify the first coordinate labels, the second coordinate labels, and the plurality of characteristic labels; generating a chart coordinate system based on the identified first coordinate labels and second coordinate labels, wherein the chart coordinate system fits the first coordinate axis and the second coordinate axis of the object image; determining coordinate values of each of the plurality of characteristic labels based on an identified position of the characteristic label in the chart coordinate system.