3 papers
cs.SD2025
Task Vector in TTS: Toward Emotionally Expressive Dialectal Speech Synthesis
Pengchao Feng, Yao Xiao, Ziyang Ma +5
Recent advances in text-to-speech (TTS) have yielded remarkable improvements in naturalness and intelligibility. Building on these achievements, research has increasingly shifted t…
cs.CL2025
MAC-SLU: Multi-Intent Automotive Cabin Spoken Language Understanding Benchmark
Yuezhang Peng, Chonghao Cai, Ziang Liu +10
Spoken Language Understanding (SLU), which aims to extract user semantics to execute downstream tasks, is a crucial component of task-oriented dialog systems. Existing SLU datasets…
cs.MM2025
ZO-ASR: Zeroth-Order Fine-Tuning of Speech Foundation Models without Back-Propagation
Yuezhang Peng, Yuxin Liu, Yao Li +3
Fine-tuning pre-trained speech foundation models for Automatic Speech Recognition (ASR) is prevalent, yet constrained by substantial GPU memory requirements. We introduce ZO-ASR, a…