SOUND SOURCE SEPARATING METHOD, APPARATUS AND DEVICE

A sound source separating method, apparatus and device. The method comprises: obtaining a first audio signal, and obtaining at least one image frame corresponding to the first audio signal, the at least one image frame comprising image information of a target sound source; and obtaining time-frequen...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: SHANG GUANGSHUANG, SUN FENGYU, CHEN LIANG
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A sound source separating method, apparatus and device. The method comprises: obtaining a first audio signal, and obtaining at least one image frame corresponding to the first audio signal, the at least one image frame comprising image information of a target sound source; and obtaining time-frequency distribution information of the target sound source in the first audio signal according to the first audio signal and the at least one image frame; furthermore, obtaining, according to the time-frequency distribution information, a second audio signal belonging to the target sound source from thefirst audio signal. According to the method, the second audio signal belonging to the target sound source can be obtained from the first audio signal relatively accurately. 本申请实施例提供一种声源分离方法、装置及设备,其中方法包括:获取第一音频信号,并获取该第一音频信号对应的至少一个图像帧,该至少一个图像帧包括目标声源的图像信息;以及,根据第一音频信号和至少一个图像帧,获取目标声源在第一音频信号中的时频分布信息;进而,根据所述时频分布信息,从所述第一音频信号中获取属于所述目标声源的第二音频信号。可以较为准确地从第一音频信号中获取属于目标声源的第二音频信号。