METHOD FOR AUTOMATICALLY IDENTIFYING DIFFERENT HUMAN VOICES IN AUDIO

Title:

METHOD FOR AUTOMATICALLY IDENTIFYING DIFFERENT HUMAN VOICES IN AUDIO

Document Type and Number:

WIPO Patent Application WO/2019/183904

Kind Code:

A1

Abstract:

Provided by the present application is a method for automatically identifying different human voices in an audio, which relates to the field of communication technology, and can automatically identify different human voices in an audio and thus helps to improve user experience. The method specifically comprises: a terminal detects a first operation in a first interface, and in response to the detected first operation, the terminal automatically identifies the human voice to which the audio content in a first file belongs; and the terminal displays a second interface, and the different human voices to which the audio content in the first file belongs have different markers in the second interface.

More Like This:

WO/2007/000816	SPEECH FEATURE EXTRACTING DEVICE, SPEAKER RECOGNIZER, PROGRAM, AND SPEECH FEATURE EXTRACTING METHOD
JP4595364	Information processing equipment and methods, programs, and recording media
JP2001501740	INDUSTRIAL APPLICABILITY A speaker voice recognition method using a predictive model for an access control application.

Inventors:

WU XIAOFANG (CN)

Application Number:

PCT/CN2018/081184

Publication Date:

October 03, 2019

Filing Date:

March 29, 2018

Export Citation:

Click for automatic bibliography generation Help

Assignee:

HUAWEI TECH CO LTD (CN)

International Classes:

G10L17/02; G10L15/30

Foreign References:

CN106448683A	2017-02-22
CN102982800A	2013-03-20
CN103530432A	2014-01-22
CN106024009A	2016-10-12

Attorney, Agent or Firm:

BEIJING ZBSD PATENT & TRADEMARK AGENT LTD. (CN)

Download PDF:

View/Download PDF PDF Help

Previous Patent: METHOD FOR TRANSMITTING DATA AND TERMINAL DEVICE

Next Patent: SIGNAL TRANSMISSION METHOD, NETWORK DEVICE, AND TERMINAL DEVICE