5 papers
SE-AGCNet: An End-to-End Framework for Joint Speech Enhancement and Loudness Control in Meeting Scenarios
Jinming Zhang, Wei Rao, Xionghu Zhong +1
Conventional audio pipelines typically treat speech enhancement (SE) and automatic gain control (AGC) as discrete modules, which often limits overall performance. For instance, app…
VoxWatermark: A Large-Scale Benchmark for Audio Watermark Detection under Perturbations
Farnaz Sedaghati, Yuxi Wang, Zicheng Weng +1
With the rapid deployment of speech generation systems in open environments, providing verifiable source attribution and copyright accountability for audio content has become criti…
Training-Free Intelligibility-Guided Observation Addition for Noisy ASR
Haoyang Li, Changsong Liu, Wei Rao +3
Automatic speech recognition (ASR) degrades severely in noisy environments. Although speech enhancement (SE) front-ends effectively suppress background noise, they often introduce…
GenTSE: Enhancing Target Speaker Extraction via a Coarse-to-Fine Generative Language Model
Haoyang Li, Xuyi Zhuang, Azmat Adnan +6
Language Model (LM)-based generative modeling has emerged as a promising direction for TSE, offering potential for improved generalization and high-fidelity speech. We propose GenT…
Joint Training or Not: An Exploration of Pre-trained Speech Models in Audio-Visual Speaker Diarization
Huan Zhao, Li Zhang, Yue Li +5
The scarcity of labeled audio-visual datasets is a constraint for training superior audio-visual speaker diarization systems. To improve the performance of audio-visual speaker dia…