LocSelect: Target Speaker Localization with an Auditory Selective Hearing Mechanism

ABSTRACT The prevailing noise-resistant and reverberation-resistant localization algorithms primarily emphasize separating and providing directional output for each speaker in multi-speaker scenarios, without association with the identity of speakers. In this paper, we present a target speaker localization algorithm with a selective hearing mechanism. Given a reference speech of the target speaker, we first produce a speaker-dependent spectrogram mask to eliminate interfering speakers' speech. Illustration of our proposed LocSelect: Given a reference network is employed to extract the target speaker's location from audio, it is capable of providing the target speaker's DoA while neglecting the filtered spectrogram. Experiments validate the superiority of our the influence from other interfering speakers through the proposed method over the existing algorithms for different scale invariant'selective hearing' mechanism.