12 papers
PitchIn: Natural-Language Vocal Coaching from Unstructured Community Feedback
Hayeon Bang, Hounsu Kim, Joonyong Park +2
Effective vocal coaching connects performance issues with corrective advice, but recordings paired with expert diagnoses and advice are scarce. Online singing communities provide a…
BenchmarkAnything: Agent-Driven Construction of Simulator-Ready Microarchitecture Benchmarks
Xiangfeng Sun, Ceyu Xu, Chen Bai +1
The selection of benchmark workloads is of paramount importance in computer architecture, as it establishes the yardstick against which architectural innovations are measured and g…
Character Identity is not Speaker Identity: KyaraBench and KyaraEmbed for Character Verification
Joonyong Park, Jerry Li
A dubbed character keeps its identity while the voice actor changes, so character identity and speaker identity are distinct properties of one recording, yet speaker verification m…
Neural Audio Codec for Robust Audio Deepfake Detection
Jungwoo Kim, Joonyong Park, Junyoung Koh +1
Audio deepfake detectors are typically evaluated on uncompressed audio, although real-world audio often undergoes low-bitrate coding. In this work, we investigate how audio coding…
Language-Statistical Analysis of Neural Audio Codec Tokens Across Architectures, Corpora, and Noise Conditions
Joonyong Park, Shinnosuke Takamichi, David M. Chan +3
Neural audio codecs (NACs) convert speech into discrete token sequences, and prior work has reported that these sequences follow language-like statistical laws. This paper analyzes…
When Does Predictor-Based RL Align with Human Perception? A Study of Subjective Rewards in Codec-Based Speech Language Models
Joonyong Park, Jerry Li
Codec-based text-to-speech (TTS) models make language-model post-training applicable to speech generation, but it remains unclear when learned perceptual predictors can serve as re…
APT: Accelerating Diffusion Transformers via Attention Probability-Guided Pruning and Quantization
Sungyeob Yoo, Seeyeon Kim, Joonyong Park +2
Recent advances in generative AI have significantly increased the demand for high-resolution image and video generation, positioning diffusion models as a core technology. Among th…
Auditing Protocol-Level Shortcuts in Large Audio Language Model Judges for Speech Evaluation
Joonyong Park, David M. Chan, Yuki Saito +1
Large audio-language models (LALMs) are increasingly used as automatic judges for speech evaluation. However, high agreement with human ratings does not guarantee that their verdic…
Probing Token Spaces under Generator Shift in AI-Generated Music Detection
Joonyong Park, Jungwoo Kim, Junyoung Koh +1
AI-generated music detectors can appear robust on standard benchmark splits, yet their deployments require transfer to generator sources absent during training. We study this probl…
AnimeScore: A Preference-Based Dataset and Framework for Evaluating Anime-Like Speech Style
Joonyong Park, Jerry Li
Evaluating 'anime-like' voices currently relies on costly subjective judgments, yet no standardized objective metric exists. A key challenge is that anime-likeness, unlike naturaln…
Analysing the Language of Neural Audio Codecs
Joonyong Park, Shinnosuke Takamichi, David M. Chan +3
This study presents a comparative analysis of the statistical and linguistic properties of neural audio codecs (NACs). We investigate discrete speech tokens produced by various NAC…
Analyzing The Language of Visual Tokens
David M. Chan, Rodolfo Corona, Joonyong Park +3
With the introduction of transformer-based models for vision and language tasks, such as LLaVA and Chameleon, there has been renewed interest in the discrete tokenized representati…