3 papers
cs.CL2026
Geometric Alignment without Functional Equivalence: A Layer-wise Analysis of the Speech-Text Modality Gap
Ming-Hao Hsu, Xueyao Zhang, Xiaohai Tian +4
End-to-end speech large language models (LLMs) often answer the same question less accurately from speech than from text, even when the spoken content matches the text prompt. Exis…
cs.CL2026
Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration
Ryan Soh-Eun Shim, Kwanghee Choi, Kalvin Chang +8
Multilingual speech foundation models such as Whisper are trained on web-scale data, where data for each language consists of a myriad of regional varieties. However, different reg…
cs.SD2025
TASLA: Text-Aligned Speech Tokens with Multiple Layer-Aggregation
Ming-Hao Hsu, Liang-Hsuan Tseng, Hung-yi Lee +1
We propose Text-Aligned Speech Tokens with Multiple Layer-Aggregation (TASLA), which is a text-aligned speech tokenization framework that aims to address the problem that under a l…