Search papers, labs, and topics across Lattice.
Affiliation:
2
0
2
1
Encoder Awakening via Adapters (EAVA), a simple yet effective domain-adaptive fine-tuning method for Speech-LLM-based ASR, consistently outperforms vanilla fine-tuning and other baselines, achieving new state-of-the-art performance.
Fine-tuned TTS models expose severe privacy risks, with membership inference attacks achieving speaker-level AUCs nearing perfect accuracy.
