4 papers · 1 filter
Detect, Attend and Extract: Keyword Guided Target Speaker Extraction
Haoyu Li, Yu Xi, Yidi Jiang +5
Target speaker extraction (TSE) aims to extract the speech of a target speaker from mixtures containing multiple competing speakers. Conventional TSE systems predominantly rely on…
USE: A Unified Model for Universal Sound Separation and Extraction
Hongyu Wang, Chenda Li, Xin Zhou +2
Sound separation (SS) and target sound extraction (TSE) are fundamental techniques for addressing complex acoustic scenarios. While existing SS methods struggle with determining th…
Time-Layer Adaptive Alignment for Speaker Similarity in Flow-Matching Based Zero-Shot TTS
Haoyu Li, Mingyang Han, Yu Xi +8
Flow-Matching (FM)-based zero-shot text-to-speech (TTS) systems exhibit high-quality speech synthesis and robust generalization capabilities. However, the speaker representation ab…
MOSA: Mixtures of Simple Adapters Outperform Monolithic Approaches in LLM-based Multilingual ASR
Junjie Li, Jing Peng, Yangui Fang +2
LLM-based ASR overcomes multilingual data scarcity by projecting speech representations into the LLM space to leverage its robust semantic and reasoning capabilities. However, whil…