5 papers
HEAR Who Said What: Unlocking Speaker-Attributed Reasoning via Counterfactual Voice Grounding
Dongwook Lee, Sangkwon Park, Eunwoo Song +6
Speech Language Models (SLMs) are increasingly deployed in multi-speaker environments, yet their ability to attribute speech to the correct speaker and reason over speaker identiti…
LILAC: An Idempotent Neural Speech Codec
June Young Yi, Dongwook Lee, Jiheum Yeom +1
Neural Audio Codecs are widely adopted in speech generation and editing. However, existing neural audio codecs are not idempotent: across the paper's twelve baseline systems, every…
Robust TTS Training via Self-Purifying Flow Matching for the WildSpoof 2026 TTS Track
June Young Yi, Hyeongju Kim, Juheon Lee
This paper presents a lightweight text-to-speech (TTS) system developed for the WildSpoof Challenge TTS Track. Our approach fine-tunes the recently released open-weight TTS model,…
SAO-Instruct: Free-form Audio Editing using Natural Language Instructions
Michael Ungersböck, Florian Grötschla, Luca A. Lanzendörfer +3
Generative models have made significant progress in synthesizing high-fidelity audio from short textual descriptions. However, editing existing audio using natural language has rem…
Training Flow Matching Models with Reliable Labels via Self-Purification
Hyeongju Kim, Yechan Yu, June Young Yi +1
Training datasets are inherently imperfect, often containing mislabeled samples due to human annotation errors, limitations of tagging models, and other sources of noise. Such labe…