Skip to content

Language-Oriented Semantic Modeling for Target Language Extraction

Mehmet Sinan Yıldırım, Ke Zhang, Shuai Wang, Haizhou Li

cs.CLarXiv:2611.26317

Abstract

Target Language Extraction (TLE) aims to isolate speech in a target language from multilingual mixtures. Existing approaches primarily rely on acoustic modeling with language identity labels, which provide only coarse categorical guidance. In this work, we propose a language-oriented semantic modeling framework that augments acoustic extraction with language-specific semantic representations. A pre-trained speech semantic model is adapted via language-aware prompt conditioning and parameter-efficient fine-tuning to generate target-language-focused semantic representations from the mixture. These capture high-level semantic structure of the acoustics and they are integrated into the extraction model to provide structured semantic guidance beyond identity labels. Experiments on the CommonVoiceMix dataset show that incorporating semantic representations consistently improves over acoustic-only baselines, achieving up to 1.16 dB SI-SDR gain.

Create a lesson