Publications

2026

DELTA-TTS: Adapting Autoregressive Model into Diffusion Language Model for Text-to-Speech
Junwon Moon, Yejin Lee, Seungbeom Kim, Hoseong Ahn, Sewoong Park, Heeseung Kim, Kyuhong Shim*
NeurIPS 2026

Forget Who You Forgot: Speaker Unlearning to Prevent Re-Identification in Zero-Shot Text-to-Speech
Hyoeun Kim, Yujun Lee, Kyuhong Shim*
NeurIPS 2026 Workshop: Beyond Private Training (InfPriv)

Tap2Listen: Instant Target Switching for Streaming Audio-Visual Speaker Extraction
Hansol Park, Minkyung Song, Zinu Kim, Yujun Lee, Hoseong Ahn, Hyunjin Choi, Kyuhong Shim*
NeurIPS 2026 Workshop: On-Device Intelligence (ODI)

StreamSE: Neural Audio Codec-based Streaming Speech Enhancement for On-Device Inference
Hyunjin Choi, Zinu Kim, Junwon Moon, Jeongyun Chae, Seungbeom Kim, Kyuhong Shim*
NeurIPS 2026 Workshop: On-Device Intelligence (ODI)

Acoustic-to-Text KV Compression for Full-Duplex Models
Yejin Lee, Seungbeom Kim, Yongha Lee, Kyuhong Shim*
NeurIPS 2026 Workshop: Real-Time Conversational Agents (RTCA)

Evaluating and Mitigating Hallucinations in Audio-Visual Multimodal LLMs with Spoken Queries
Hansol Park, Hoseong Ahn, Junwon Moon, Yejin Lee, Kyuhong Shim*
NeurIPS 2026 Workshop: Vision-Language Models for Real-World Deployment (VLM4RWD)

Whisper-CD: Accurate Long-Form Speech Recognition using Multi-Negative Contrastive Decoding
Hoseong Ahn, Jeongyun Chae, Yoonji Park, Kyuhong Shim*
INTERSPEECH 2026

WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models
Hanna Lee, Tan Dat Nguyen, Jaehoon Kang, Kyuhong Shim*
INTERSPEECH 2026

DialBGM: A Benchmark for Background Music Recommendation from Everyday Multi-Turn Dialogues
Joonhyeok Shin, Jaehoon Kang, Yujun Lee, Hanna Lee, Yejin Lee, Yoonji Park, Kyuhong Shim*
ICML 2026 Workshop: Machine Learning for Audio (ML4Audio)

Beyond Binary Instrument QA: Probing Instrument Grounding in Music Audio-Language Models
Yujun Lee, Joonhyeok Shin, Hyoeun Kim, Kyuhong Shim*
ICML 2026 Workshop: Machine Learning for Audio (ML4Audio)

Encoder-Free Style Controllable Text-to-Speech with Voice Attribute Vectors
Jaehoon Kang, Yejin Lee, Kyuhong Shim*
ICEIC 2026

Famigo: A Privacy-Preserving Hybrid Voice Assistant for Multi-User Family Environments
Hoseong Ahn, Hansol Park, Junwon Moon, Kihun Lee, Kyuhong Shim*
ICEIC 2026

Mask2Flow-TSE: Two-Stage Target Speaker Extraction with Masking and Flow Matching
Junwon Moon, Seungbeom Kim, Hyunjin Choi, Hansol Park, Heeseung Kim, Kyuhong Shim*
arXiv preprint

Unlocking Fine-Grained and Within-Utterance Speaking Style Control in Prompt-Based Text-to-Speech Models
Jaehoon Kang, Yejin Lee, Yoonji Park, Kyuhong Shim*
arXiv preprint

TLDR: Compressing Audio Tokens for Efficient Autoregressive Text-to-Speech
Yejin Lee, Junwon Moon, Hyoeun Kim, Hyunjin Choi, Heeseung Kim, Kyuhong Shim*
arXiv preprint

GLASS: GRPO-Trained LoRA for Acoustic Style Steering in Zero-Shot Text-to-Speech
Jaehoon Kang, Yejin Lee, Kyuhong Shim*
arXiv preprint

2025

P2VA: Converting Persona Descriptions into Voice Attributes for Fair and Controllable Text-to-Speech
Yejin Lee, Jaehoon Kang, Kyuhong Shim*
arXiv preprint