Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
SPAR-K: Scheduled Periodic Alternating Early Exit for Spoken Language Models
Hsiao-Ying Huang, Cheng-Han Chiang, Hung-yi Lee
Interleaved spoken language models (SLMs) alternately generate text and speech tokens, but decoding at full transformer depth for every step becomes costly, especially due to long…
cs.CL2025
MI-Fuse: Label Fusion for Unsupervised Domain Adaptation with Closed-Source Large-Audio Language Model
Hsiao-Ying Huang, Yi-Cheng Lin, Hung-yi Lee
Large audio-language models (LALMs) show strong zero-shot ability on speech tasks, suggesting promise for speech emotion recognition (SER). However, SER in real-world deployments o…