5 papers
Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
Siddhant Arora, Haidar Khan, Kai Sun +14
End-to-end speech-in speech-out dialogue systems are emerging as a powerful alternative to traditional ASR-LLM-TTS pipelines, generating more natural, expressive responses with sig…
PIRF: Physics-Informed Reward Fine-Tuning for Diffusion Models
Mingze Yuan, Pengfei Jin, Na Li +1
Diffusion models have demonstrated strong generative capabilities across scientific domains, but often produce outputs that violate physical laws. We propose a new perspective by f…
MBCodec:Thorough disentangle for high-fidelity audio compression
Ruonan Zhang, Xiaoyang Hao, Yichen Han +3
High-fidelity neural audio codecs in Text-to-speech (TTS) aim to compress speech signals into discrete representations for faithful reconstruction. However, prior approaches faced…
Multi-Channel Differential ASR for Robust Wearer Speech Recognition on Smart Glasses
Yufeng Yang, Yiteng Huang, Yong Xu +9
With the growing adoption of wearable devices such as smart glasses for AI assistants, wearer speech recognition (WSR) is becoming increasingly critical to next-generation human-co…
Offline Imitation Learning upon Arbitrary Demonstrations by Pre-Training Dynamics Representations
Haitong Ma, Bo Dai, Zhaolin Ren +2
Limited data has become a major bottleneck in scaling up offline imitation learning (IL). In this paper, we propose enhancing IL performance under limited expert data by introducin…