End-to-end speech-to-text retrieval is becoming an important capability for voice agents, allowing spoken queries to retrieve relevant documents without intermediate transcription. Training these retrievers typically depends on large collections of spoken query-document pairs that are costly to acquire and difficult to...
Sangkwon Park, Dongwook Lee, Younghoon Cho et al.· 0 citations
Wearable augmented reality (AR) assistants are moving toward continuous real-world interaction, where they perceive the user's activity through first-person video and audio and provide timely spoken guidance without being explicitly asked. While proactive video assistants, spoken dialog systems, and egocentric task und...
Phrase-Localized Language-Contrastive Guidance (LCG), a training-free inference framework that restores a native accent to code-switched phrases in cross-lingual text-to-speech, robustly increases the nativeness of the code-switched phrase while suppressing accent leakage, and preserving overall speaker identity and na...
C. Lee, Sangkwon Park, Donghun Kang et al.· 1 citation
A2R, a 30B model optimized on Counterfactual Audio with Speaker-level Hard negatives (CASH), a dataset designed to guide the model to prioritize acoustic vocal cues over linguistic signals, achieves strong performance on HEAR and exhibits zero-shot generalization to diverse multi-speaker downstream tasks, demonstrating...
Dongwook Lee, Sangkwon Park, Eunwoo Song et al.· 0 citations
DELTA-TTS is introduced, a lightweight LoRA-based adaptation framework that converts a pretrained AR TTS model into a discrete diffusion language model (dLLM) for confidence-ordered speech-token decoding and produces sharper text--speech alignment, increases overall decoding confidence, and mitigates the hallucinations...
Junwon Moon, Yejin Lee, Seungbeom Kim et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
