7 papers
The ISCSLP 2026 Real-World Audio-Visual Speech Enhancement Challenge: A Benchmark with Natural Mixtures and Degraded Video
Kai Li, Wenze Ren, Junjie Li +11
Audio-visual speech enhancement (AVSE) uses a target speaker's visible articulation to recover that speaker's voice from overlapped speech. Yet most evaluation protocols rely on sy…
EmoShift: Lightweight Activation Steering for Enhanced Emotion-Aware Speech Synthesis
Li Zhou, Hao Jiang, Junjie Li +2
Achieving precise and controllable emotional expression is crucial for producing natural and context-appropriate speech in text-to-speech (TTS) synthesis. However, many emotion-awa…
MeMo: Attentional Momentum for Real-Time Audio-Visual Target Speaker Extraction Under Impaired Visual Conditions
Junjie Li, Wenxuan Wu, Shuai Wang +4
Audio-visual Target Speaker Extraction (AV-TSE) aims to isolate a target speaker's voice from multi-speaker environments by leveraging visual cues as guidance. However, the perform…
Do We Really Need GNNs with Explicit Structural Modeling? MLPs Suffice for Language Model Representations
Li Zhou, Hao Jiang, Junjie Li +4
Explicit structural information has been proven to be encoded by Graph Neural Networks (GNNs), serving as auxiliary knowledge to enhance model capabilities and improve performance…
MoMuSE: Momentum Multi-modal Target Speaker Extraction for Real-time Scenarios with Impaired Visual Cues
Junjie Li, Ke Zhang, Shuai Wang +3
Audio-visual Target Speaker Extraction (AV-TSE) aims to isolate the speech of a specific target speaker from an audio mixture using time-synchronized visual cues. In real-world sce…
Multi-Level Speaker Representation for Target Speaker Extraction
Ke Zhang, Junjie Li, Shuai Wang +4
Target speaker extraction (TSE) relies on a reference cue of the target to extract the target speech from a speech mixture. While a speaker embedding is commonly used as the refere…
On the effectiveness of enrollment speech augmentation for Target Speaker Extraction
Junjie Li, Ke Zhang, Shuai Wang +3
Deep learning technologies have significantly advanced the performance of target speaker extraction (TSE) tasks. To enhance the generalization and robustness of these algorithms wh…