Humans possess the remarkable ability to selectively attend to a single speaker amidst
competing voices and background noise, known as selective auditory attention. Recent …

A speaker extraction algorithm seeks to extract the speech of a target speaker from a multi-
talker speech mixture when given a cue that represents the target speaker, such as a pre …

Target speech extraction (TSE) systems are designed to extract target speech from a multi-
talker mixture. The popular training objective for most prior TSE networks is to enhance …

In target speaker extraction, many studies rely on the speaker embedding which is obtained
from an enrollment of the target speaker and employed as the guidance. However, solely …

Most target speaker extraction methods use the target speaker embedding as reference
information. However, the speaker embedding extracted by a speaker recognition module …

Target speaker extraction (TSE) which has the capability to directly extract desired speech
given enrollment utterances of the target speaker has attracted more and more attention for …

Speech signals are inherently complex as they encompass both global acoustic
characteristics and local semantic information. However, in the task of target speech …

FullSubNet has shown its promising performance on speech enhancement by utilizing both
fullband and subband information. However, the relationship between fullband and subband …

The goal of target speaker extraction (TSE) is to extract the target speaker's voice from the
mixture speech of multiple speakers. It needs to enroll the speech of the target speaker in …

The previous SpEx+ has yielded outstanding performance in speaker extraction and
attracted much attention. However, it still encounters inadequate utilization of multi-scale …