Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
MC-MRX: Reference- and Midi-Guided Music Source Extraction with Contrastive LearningAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21A hybrid discriminative and generative system for Universal speech enhancementAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Beyond Lips: Integrating Gesture and Lip Cues for Robust Audio-Visual Speaker ExtractionAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21ArtiFree: Detecting and Reducing Generative Artifacts in Diffusion-Based Speech EnhancementMeta · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Mongoose: do we Need a Scanner for Vision Mamba?Microsoft · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Efficient Distillation of Large Language Models Using Group Relative Policy DistillationAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Streaming Speech Recognition with Decoder-Only Large Language Models and Latency OptimizationiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Equipping Large Language Model with Directional Speech Understanding CapabilitiesMeta · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Hadamard Tensor Ring for Efficient Low-Rank Fine-TuningAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21CIP-DoA: Cross-Instance Prompted DoA Estimation via Semantic-Spatial MatchingAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21One-Step Generative DistillationAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21A Comprehensive Ecosystem for Open-Domain Customized Video GenerationMicrosoft · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Mitigating Deceptive Knowledge Editing in LLMS via Diffusion SynthesisAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Evaluating ASR-LLM Setups for Japanese Speech Recognition with Multi-Pass Augmented Generative Error CorrectionNVIDIA · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Align2speak: Improving TTS for Low Resource Languages via ASR-Guided Online Preference OptimizationNVIDIA · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21LuSeeL: Language-Queried Binaural Universal Sound Event Extraction and LocalizationAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Artifact-Aware Evaluation for High-Quality Video GenerationAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Ensuring Reliable Participation in Subjective Video Quality Tests Across PlatformsMicrosoft · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Advancing Speech Summarization in Multi-Modal LLMs with Reinforcement LearningMicrosoft · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Denoising Of Stochastic Ray Tracing Room Impulse ResponsesMeta · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21CoVA: Text-Guided Composed Video Retrieval for Audio-Visual ContentGoogle DeepMind · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Discrete Diffusion for Generative Modeling of Text-Aligned Speech TokensNVIDIA · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Dare: Dual-Aspect Reflective Evolution for Prompt OptimizationAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Fourier Pruning for Large Language Models CompressionAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21LESS: Large Language Model Enhanced Semi-Supervised Learning for Speech Foundational Models Using in-the-wild DataNVIDIA · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21