8 papers
AudioRAG+: Feedback-driven Retrieval-augmented Audio Generation with Large Audio Language Models
Junqi Zhao, Chenxing Li, Jinzheng Zhao +4
We propose a general feedback-driven retrieval-augmented generation (RAG) approach that leverages Large Audio Language Models (LALMs) to address the missing or imperfect synthesis…
Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access
Xiang Hu, Jiaqi Leng, Jun Zhao +2
A key advantage of Recurrent Neural Networks (RNNs) over Transformers is their linear computational and space complexity enables faster training and inference for long sequences. H…
Region-Specific Audio Tagging for Spatial Sound
Jinzheng Zhao, Yong Xu, Haohe Liu +6
Audio tagging aims to label sound events appearing in an audio recording. In this paper, we propose region-specific audio tagging, a new task which labels sound events in a given r…
WTFormer: A Wavelet Conformer Network for MIMO Speech Enhancement with Spatial Cues Peservation
Lu Han, Junqi Zhao, Renhua Peng
Current multi-channel speech enhancement systems mainly adopt single-output architecture, which face significant challenges in preserving spatio-temporal signal integrity during mu…
Impact of Frame Rates on Speech Tokenizer: A Case Study on Mandarin and English
Haoyang Zhang, Hexin Liu, Xiangyu Zhang +7
The speech tokenizer plays a crucial role in recent speech tasks, generally serving as a bridge between speech signals and language models. While low-frame-rate codecs are widely e…
AudioTurbo: Fast Text-to-Audio Generation with Rectified Diffusion
Junqi Zhao, Jinzheng Zhao, Haohe Liu +5
Diffusion models have significantly improved the quality and diversity of audio generation but are hindered by slow inference speed. Rectified flow enhances inference speed by lear…