activity
20222026
most citedExploring Effective Distillation of Self-Supervised Speech Models for Automatic Speech Recognition

2 citations · 2 across the 6 of their papers we have counts for

collaborators
Showing 2026Show all

2 papers · 1 filter

cs.CL2026

Rethinking Length-Based Training: Batch Composition and Loss Normalization in Speech Token Language Models

Hongjin Song, Runwu Shi, Weiqiao Shan +4

Short-to-long training is a simple curriculum for speech models, but its gains can be difficult to interpret. In speech token language models, length-based training can change the…

eess.AS2026

Joint Residual Reweighting for Classifier Free Guidance in Flow-Matching Zero-Shot TTS

Runwu Shi, Yujin Wang, Hongjin Song +8

Classifier-free guidance (CFG) is widely used in flow-matching-based zero-shot text-to-speech (TTS), where generation is conditioned on text content and a speech prompt. Standard C…