5 papers
MoLGE: Mixture of Language Group Experts for Efficient Scaling of Massively Multilingual Speech Recognition
Sangmin Lee, Woojin Chung, Woongjib Choi +1
Massively multilingual automatic speech recognition (ASR) models covering hundreds of languages must maintain robust performance across diverse linguistic and acoustic conditions.…
UR-BERT: Scaling Text Encoders for Massively Multilingual TTS Through Universal Romanization and Speech Token Prediction
Sangmin Lee, Eekgyun Ahn, Woongjib Choi +1
We propose UR-BERT, a Romanized transcription-based text-to-speech (TTS) encoder for massively multilingual TTS systems. Conventional grapheme-to-phoneme (G2P)-based approaches are…
UniverSR: Unified and Versatile Audio Super-Resolution via Vocoder-Free Flow Matching
Woongjib Choi, Sangmin Lee, Hyungseob Lim +1
In this paper, we present a vocoder-free framework for audio super-resolution that employs a flow matching generative model to capture the conditional distribution of complex-value…
SAGE-LD: Towards Scalable and Generalizable End-to-End Language Diarization via Simulated Data Augmentation
Sangmin Lee, Woongjib Choi, Jihyun Kim +1
In this paper, we present a neural spoken language diarization model that supports an unconstrained span of languages within a single framework. Our approach integrates a learnable…
Neural Spectral Band Generation for Audio Coding
Woongjib Choi, Byeong Hyeon Kim, Hyungseob Lim +2
Spectral band replication (SBR) enables bit-efficient coding by generating high-frequency bands from the low-frequency ones. However, it only utilizes coarse spectral features upon…