collaborators

9 papers

cs.SD2026

Online Register for Dual-Mode Self-Supervised Speech Models: Mitigating The Lack of Future Context

Keita Goto, Takashi Maekaku, Jin Sakuma +3

Dual-mode self-supervised speech models (S3Ms), which jointly pre-trained in the offline and online mode, suffer from attention mismatch in streaming scenarios due to missing futur…

eess.AS2026

Reasoning Beyond Majority Vote: An Explainable SpeechLM Framework for Speech Emotion Recognition

Bo-Hao Su, Hui-Ying Shih, Jinchuan Tian +4

Speech Emotion Recognition (SER) is typically trained and evaluated on majority-voted labels, which simplifies benchmarking but masks subjectivity and provides little transparency…

cs.SD2026

Do Neural Codecs Generalize? A Controlled Study Across Unseen Languages and Non-Speech Tasks

Shih-Heng Wang, Jiatong Shi, Jinchuan Tian +2

This paper investigates three crucial yet underexplored aspects of the generalization capabilities of neural audio codecs (NACs): (i) whether NACs can generalize to unseen language…

cs.SD2025

PURE Codec: Progressive Unfolding of Residual Entropy for Speech Codec Learning

Jiatong Shi, Haoran Wang, William Chen +4

Neural speech codecs have achieved strong performance in low-bitrate compression, but residual vector quantization (RVQ) often suffers from unstable training and ineffective decomp…

eess.AS2025

BSCodec: A Band-Split Neural Codec for High-Quality Universal Audio Reconstruction

Haoran Wang, Jiatong Shi, Jinchuan Tian +3

Neural audio codecs have recently enabled high-fidelity reconstruction at high compression rates, especially for speech. However, speech and non-speech audio exhibit fundamentally…

cs.SD2025

Evaluating Self-Supervised Speech Models via Text-Based LLMS

Takashi Maekaku, Keita Goto, Jinchuan Tian +2

Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, asses…