Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation
Chan-Jan Hsu, Liang-Hsuan Tseng, Yi-Cheng Lin +5
Generative spoken language models pretrained on large-scale raw audio can continue a speech prompt with appropriate content while preserving attributes like speaker and emotion, se…
cs.CL2026
TASTE-Streaming: Towards Streamable Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
Liang-Hsuan Tseng, Hung-yi Lee
Text-speech joint spoken language modeling (SLM) aims at natural and intelligent speech-based interactions, but developing such a system may suffer from modality mismatch: speech u…