Publications

2026

1. COLM

   MoLGE: Mixture of Language Group Experts for Efficient Scaling of Massively Multilingual Speech Recognition

   Sangmin Lee, Woojin Chung, Woongjib Choi, and Hong-Goo Kang

   In Conference on Language Modeling (COLM), 2026
2. INTERSPEECH

   UR-BERT: Scaling Text Encoders for Massively Multilingual TTS Through Universal Romanization and Speech Token Prediction

   Sangmin Lee, Eekgyun Ahn, Woongjib Choi, and Hong-Goo Kang

   In INTERSPEECH, 2026

   LINK
3. ICASSP

   UniverSR: Unified and Versatile Audio Super-Resolution via Vocoder-Free Flow Matching

   Woongjib Choi, Sangmin Lee, Hyungseob Lim, and Hong-Goo Kang

   In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026

   Code LINK Demo

2025

1. Preprint

   SAGE-LD: Towards Scalable and Generalizable End-to-End Language Diarization via Simulated Data Augmentation

   Sangmin Lee, Woongjib Choi, Jihyun Kim, and Hong-Goo Kang

   arXiv preprint, 2025

   LINK
2. INTERSPEECH

   Neural Spectral Band Generation for Audio Coding

   Woongjib Choi, Byeong Hyeon Kim, Hyungseob Lim, Inseon Jang, and Hong-Goo Kang

   In INTERSPEECH, 2025

   LINK

2024

1. Domestic

   DNN-based Speech Codec Enhancement Utilizing Conditional Flow Matching

   Jaehoon Shin, Woongjib Choi, Byeong Hyeon Kim, Inseon Jang, and Hong-Goo Kang

   In Proceedings of the Korean Institute of Broadcast and Media Engineers (KIBME) Conference, 2024

   Abs LINK

   본 논문에서는 신호처리 기반 음성 코덱의 낮은 비트전송률에서의 복원 품질을 향상하기 위해 조건부 플로우 매칭 기반의 후처리 필터를 적용하고 그 효과를 확인한다. 최근 확산 기반 생성 모델을 활용하여 오디오 코덱의 손실 압축으로 인해 왜곡된 신호의 품질을 향상하는 연구가 이루어지고 있으나, 주로 신경망 기반 오디오 코덱에 편중되어 있으며 기존 상용 코덱에 대한 적용 사례는 부족하다. 본 연구에서는 플로우 매칭 기반 생성 모델을 신호처리 기반 음성 코덱의 후처리 필터로 적용하여, 낮은 비트전송률에서도 높은 비트전송률의 복원 품질에 준하는 품질 개선을 달성하고자 한다. 또한, 품질 개선 폭을 최대한 유지하면서 연산량의 효율성을 확보하기 위한 경량화 방법을 탐구하였으며, 실험을 통해 제안한 방법의 타당성을 확인하였다.

2. Domestic

   Non-Blind Speech Bandwidth Extension Using Pre-Trained Self-Supervised Features

   Woongjib Choi, Byeong Hyeon Kim, and Hong-Goo Kang

   In Proceedings of the Institute of Electronics and Information Engineers (IEIE) Conference, 2024

   Abs LINK

   Bandwidth extension (BWE) is a technique that estimates high-frequency components from provided low-frequency components. Most existing deep neural network-based BWE methods rely solely on information from the band-limited audio signal. Drawing inspiration from spectral band replication (SBR), we propose a novel BWE framework that employs self-supervised pre-trained features as conditional inputs in the BWE process. Our experiments demonstrate that the proposed approach outperforms the baseline SEANet architecture in terms of log-spectral distance (LSD) and PESQ. Additionally, we explore the methodologies for extracting and quantizing self-supervised learning (SSL) features to effectively utilize them as conditional inputs.