5 papers
CoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models
Yingzhuo Deng, Chong Li, Bingxin Liu +6
Spoken Dialogue Models (SDMs) typically share a speech-token space for generation and synthesis, leading to long autoregressive sequences and costly inference. Lower-rate speech to…
VibeVoice-ASR-Streaming Technical Report
Yujie Tu, Zhiliang Peng, Jianwei Yu +11
Traditional speaker-attributed ASR systems treated ASR and speaker diarization as two separate tasks. Recently, end-to-end models such as VibeVoice-ASR have unified the two tasks w…
DialectS2S: End-to-End Speech Dialogue Modeling for Low-Resource Chinese Dialects
Yi Shu, Tianyu Peng, Yingzhuo Deng +5
Current end-to-end speech dialogue models are primarily optimized for mainstream languages and remain limited in low-resource dialect scenarios due to the scarcity of dialect speec…
OpenS2S: Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model
Chen Wang, Tianyu Peng, Wen Yang +8
Empathetic interaction is a cornerstone of human-machine communication, due to the need for understanding speech enriched with paralinguistic cues and generating emotional and expr…
Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution Alignment
Tianyu Peng, Jiajun Zhang
Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones. However, the multi…