10 papers
MemeLogos: Knowledge-Driven Retrieval-Augmented Reasoning for Harmful Meme Detection
Hexiang Gu, Saihui Hou, Changlan Liu +4
With the rapid proliferation of social media, harmful memes have become a growing threat to online ecosystems. Their harmfulness is often implicitly conveyed through complex intera…
G-MaP-SE: Guided Speech Enhancement via GMM-Based Prior Matching
Yike Zhu, Ziqian Wang, Zikai Liu +5
Using speaker embeddings as conditioning can strengthen speech enhancement, but most methods either require clean enrollment audio or rely on embeddings extracted from noisy speech…
EvoTSE: Evolving Enrollment for Target Speaker Extraction
Zikai Liu, Ziqian Wang, Xingchen Li +4
Target Speaker Extraction (TSE) aims to isolate a specific speaker's voice from a mixture, guided by a pre-recorded enrollment. While TSE bypasses the global permutation ambiguity…
LSZone: A Lightweight Spatial Information Modeling Architecture for Real-time In-car Multi-zone Speech Separation
Jun Chen, Shichao Hu, Jiuxin Lin +8
In-car multi-zone speech separation, which captures voices from different speech zones, plays a crucial role in human-vehicle interaction. Although previous SpatialNet has achieved…
MeanFlowSE: One-Step Generative Speech Enhancement via MeanFlow
Yike Zhu, Boyi Kang, Ziqian Wang +6
Speech enhancement (SE) recovers clean speech from noisy signals and is vital for applications such as telecommunications and automatic speech recognition (ASR). While generative a…
SenSE: Semantic-Aware High-Fidelity Universal Speech Enhancement
Xingchen Li, Hanke Xie, Ziqian Wang +4
Generative Universal Speech Enhancement (USE) methods aim to leverage generative models to improve speech quality under various types of distortions. However, existing generative s…
UniFlow: Unifying Speech Front-End Tasks via Continuous Generative Modeling
Ziqian Wang, Zikai Liu, Yike Zhu +6
Generative modeling has recently achieved remarkable success across image, video, and audio domains, demonstrating powerful capabilities for unified representation learning. Yet sp…
EchoFree: Towards Ultra Lightweight and Efficient Neural Acoustic Echo Cancellation
Xingchen Li, Boyi Kang, Ziqian Wang +4
In recent years, neural networks (NNs) have been widely applied in acoustic echo cancellation (AEC). However, existing approaches struggle to meet real-world low-latency and comput…
AISHELL-5: The First Open-Source In-Car Multi-Channel Multi-Speaker Speech Dataset for Automatic Speech Diarization and Recognition
Yuhang Dai, He Wang, Xingchen Li +8
This paper delineates AISHELL-5, the first open-source in-car multi-channel multi-speaker Mandarin automatic speech recognition (ASR) dataset. AISHLL-5 includes two parts: (1) over…
DualSep: A Light-weight dual-encoder convolutional recurrent network for real-time in-car speech separation
Ziqian Wang, Jiayao Sun, Zihan Zhang +3
Advancements in deep learning and voice-activated technologies have driven the development of human-vehicle interaction. Distributed microphone arrays are widely used in in-car sce…