Continuous audio encoders compress audio along feature and time axes through latent width and frame rate, but their joint effect on downstream performance remains unclear. We train sixteen encoders spanning four widths and four frame rates, with downstream adapters and probes, using matched training protocols. Despite...
Kyudan Jung, Sehyun Lee, Song-ha Jo et al.· 0 citations
As human--AI interactions become more conversational, full-duplex speech language models capable of natural real-time dialogue are growing in importance. Beyond generating appropriate responses, these models must coordinate turn-taking, backchanneling, and floor management in real time. Reinforcement learning (RL) prov...
Kyudan Jung, Hyunsin Park, Yoonhyung Lee et al.· 0 citations
Recent audio deepfake detectors separate bona fide speech from synthetic speech, yet it remains unclear which stage of a text-to-speech system supplies the detection evidence. We address this with controlled resynthesis and detector adaptation in an F5-TTS-BigVGAN pipeline. Since vocoder reconstruction of a real mel ca...
Eunji Shin, Kyudan Jung, Jihwan Kim et al.· 0 citations
SNAP, a speaker-nulling framework, is introduced that reduces speaker entanglement and encourages detectors to focus on artifact-related patterns, leading to state-of-the-art performance.
Kyudan Jung, Ji-Hoon Kim, Minwoo Lee et al.· arXiv.org· 0 citations
OmniACBench, a benchmark for evaluating context-grounded acoustic control in omni-modal models, is introduced and three common failure modes are identified-weak direct control, failed implicit inference, and failed multimodal grounding-providing insights for developing models that can verbalize responses effectively.
Seunghee Kim, B. Park, Kyudan Jung et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
