Inter-Speaker Relative Cues for Two-Stage Text-Guided Target Speech Extraction

This paper investigates the use of relative cues for text-based target speech extraction (TSE). We first provide a theoretical justification for relative cues from the perspectives of human perception and label quantization, showing that relative cues preserve fine-grained distinctions that are often lost in absolute categorical representations for continuous-valued attributes. Building on this analysis, we propose a two-stage TSE framework in which a speech separation model first generates candidate sources, followed by a text-guided classifier that selects the target speaker based on embedding similarity. Within this framework, we train two separate classification models to evaluate the advantages of relative cues over independent cues in case of continuous-valued attributes, considering both classification accuracy and TSE performance. Experimental results demonstrate that (i) relative cues achieve higher overall classification accuracy and improved TSE performance compared with independent cues; (ii) the proposed two-stage framework substantially outperforms single-stage text-conditioned extraction methods on both signal-level and objective perceptual metrics; and (iii) several relative cues, including language, loudness, distance, temporal order, speaking duration, random cues, and all cues, can even surpass the performance of an enrollment-audio-based TSE system. Further analysis reveals notable differences in discriminative power across cue types, providing insights into the effectiveness of different relative cues for TSE.