8 papers
Tracing and Relearning Detection Evidence in Text-to-Speech Systems
Eunji Shin, Kyudan Jung, Jihwan Kim +2
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 a…
EditPPT: Structured Execution and Evaluation for Reliable Slide Editing
Jiheon Kim, Kyudan Jung, Jaegul Choo
Reliable slide editing requires precise modifications to intended objects while preserving the rest of the presentation. We argue that slide editing is a problem of structured, con…
Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models
Kyudan Jung, Jihwan Kim, Soyoon Kim +3
As the paradigm of AI shifts from text-based LLMs to Speech Language Models (SLMs), there is a growing demand for full-duplex systems capable of real-time, natural human-computer i…
SLICE: Speech Enhancement via Layer-wise Injection of Conditioning Embeddings
Seokhoon Moon, Kyudan Jung, Jaegul Choo
Real-world speech is often corrupted by multiple degradations simultaneously, including additive noise, reverberation, and nonlinear distortion. Diffusion-based enhancement methods…
OmniACBench: A Benchmark for Evaluating Context-Grounded Acoustic Control in Omni-Modal Models
Seunghee Kim, Bumkyu Park, Kyudan Jung +5
Most testbeds for omni-modal models assess multimodal understanding via textual outputs, leaving it unclear whether these models can properly speak their answers. To study this, we…
SNAP: Speaker Nulling for Artifact Projection in Speech Deepfake Detection
Kyudan Jung, Jihwan Kim, Minwoo Lee +4
Recent advancements in text-to-speech technologies enable generating high-fidelity synthetic speech nearly indistinguishable from real human voices. While recent studies show the e…
Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulation
Kyudan Jung, Hojun Cho, Jooyeol Yun +3
Editing presentation slides is a frequent yet tedious task, ranging from creative layout design to repetitive text maintenance. While recent GUI-based agents powered by Multimodal…
Fast Fourier Transform-Based Spectral and Temporal Gradient Filtering for Differential Privacy
Hyeju Shin, Vincent-Daniel, Kyudan Jung +1
Differential Privacy (DP) has emerged as a key framework for protecting sensitive data in machine learning, but standard DP-SGD often suffers from significant accuracy loss due to…