7 papers
Positive-Incentive Noise Predictor for Adversarial Purification in Speaker Verification
Yibo Bai, Sizhou Chen, Michele Panariello +5
Modern automatic speaker verification (ASV) systems are vulnerable to adversarial perturbations. Diffusion-based purification has recently shown strong effectiveness against such p…
High-Fidelity Generative Audio Compression at 0.275kbps
Hao Ma, Ruihao Jing, Shansong Liu +4
High-fidelity general audio compression at ultra-low bitrates is crucial for applications ranging from low-bandwidth communication to generative audio-language modeling. Traditiona…
Bridging the Gap between Continuous and Informative Discrete Representations by Random Product Quantization
Xueqing Li, Hao Ma, Zehan Li +8
Self-supervised learning (SSL) has become a core technique in speech processing, but the high dimensionality of its representations makes discretization essential for improving eff…
Towards Multimodal Query-Based Spatial Audio Source Extraction
Chenxin Yu, Hao Ma, Xu Li +4
Query-based audio source extraction seeks to recover a target source from a mixture conditioned on a query. Existing approaches are largely confined to single-channel audio, leavin…
Enhancing Intelligibility for Generative Target Speech Extraction via Joint Optimization with Target Speaker ASR
Hao Ma, Rujin Chen, Xiao-Lei Zhang +2
Target speech extraction (TSE) isolates the speech of a specific speaker from a multi-talker overlapped speech mixture. Most existing TSE models rely on discriminative methods, typ…
Language-Queried Target Sound Extraction Without Parallel Training Data
Hao Ma, Zhiyuan Peng, Xu Li +4
Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extens…