7 papers
FineLAP: Taming Heterogeneous Supervision for Fine-grained Language-Audio Pretraining
Xiquan Li, Xuenan Xu, Ziyang Ma +4
Contrastively pretrained audio-language models (e.g., CLAP) excel at clip-level understanding but struggle with frame-level tasks. Existing extensions fail to exploit the varying g…
Resonate: Reinforcing Text-to-Audio Generation via Online Feedback from Large Audio Language Models
Xiquan Li, Junxi Liu, Wenxi Chen +3
Reinforcement Learning (RL) has become an effective paradigm for enhancing Large Language Models (LLMs) and visual generative models. However, its application in text-to-audio (TTA…
Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation
Pengchao Feng, Ziyang Ma, Wenxi Chen +4
End-to-end speech-to-speech (S2S) dialogue systems have recently garnered increasing research attention for their lower latency and more natural integration of nonverbal cues such…
MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows
Xiquan Li, Junxi Liu, Yuzhe Liang +3
Recent years have witnessed remarkable progress in Text-to-Audio Generation (TTA), providing sound creators with powerful tools to transform inspirations into vivid audio. Yet desp…
SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation
Keqi Deng, Wenxi Chen, Xie Chen +1
Simultaneous speech translation (SST) outputs translations in parallel with streaming speech input, balancing translation quality and latency. While large language models (LLMs) ha…
DRCap: Decoding CLAP Latents with Retrieval-Augmented Generation for Zero-shot Audio Captioning
Xiquan Li, Wenxi Chen, Ziyang Ma +5
While automated audio captioning (AAC) has made notable progress, traditional fully supervised AAC models still face two critical challenges: the need for expensive audio-text pair…