5 papers · 1 filter
JASTIN: Aligning LLMs for Zero-Shot Audio and Speech Evaluation via Natural Language Instructions
Leying Zhang, Bowen Shi, Haibin Wu +2
The rapid advancement of generative audio models has outpaced the development of robust evaluation methodologies. Existing objective metrics and general multimodal large language m…
SLIDE: Integrating Speech Language Model with LLM for Spontaneous Spoken Dialogue Generation
Haitian Lu, Gaofeng Cheng, Liuping Luo +3
Recently, ``textless" speech language models (SLMs) based on speech units have made huge progress in generating naturalistic speech, including non-verbal vocalizations. However, th…
Scale This, Not That: Investigating Key Dataset Attributes for Efficient Speech Enhancement Scaling
Leying Zhang, Wangyou Zhang, Chenda Li +1
Recent speech enhancement models have shown impressive performance gains by scaling up model complexity and training data. However, the impact of dataset variability (e.g. text, la…
CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations
Leying Zhang, Yao Qian, Long Zhou +9
Recent advancements in zero-shot text-to-speech (TTS) modeling have led to significant strides in generating high-fidelity and diverse speech. However, dialogue generation, along w…
DDTSE: Discriminative Diffusion Model for Target Speech Extraction
Leying Zhang, Yao Qian, Linfeng Yu +5
Diffusion models have gained attention in speech enhancement tasks, providing an alternative to conventional discriminative methods. However, research on target speech extraction u…