Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Intrinsic Semantic Consistency Enhancement for Robust Hierarchical Understanding in VLMsSenseTime · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21SatBadEdit: Towards Efficient and Robust Multi-Trigger Backdoor Injection in Large Language ModelsAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21FinMCP-Bench: Benchmarking LLM Agents for Real-World Financial Tool Use Under the Model Context ProtocolAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21DemoReranker: Enhancing the in-Context Learning Capability of Multi-Modal Large Models VIA Demo RankingiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Latent Temporal Discrepancy as Motion Prior: A Loss-Weighting Strategy for Dynamic Fidelity in T2VAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21T-Mimi: A Transformer-Based Mimi Decoder for Real-Time On-Phone TTSMeta · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Fine-Grained Text-to-Image Synthesis with Semantic RefinementAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Few-Shot and Pseudo-Label Guided Speech Quality Evaluation with Large Language ModelsNVIDIA · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Boosting Knowledge Sharing Among Agents via Graph DecouplingAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Multi-Domain Audio Question Answering Benchmark toward Acoustic Content ReasoningNVIDIA · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Phrased: Phrase Dictionary Biasing for Speech TranslationMicrosoft · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Chromouvqa: Benchmarking Vision-Language Models under Chromatic Camouflaged ImagesAlphabet · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21MELA-TTS: Joint Transformer-Diffusion Model with Representation Alignment for Speech SynthesisAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21How Does Instrumental Music Help Singfake Detection?NVIDIA · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Controlling Language Difficulty in Dialogues with Linguistic FeaturesAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Salad-VAE: Semantic Audio Compression with Language-Audio DistillationMicrosoft · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AISakana AI · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Generalizability of Predictive and Generative Speech Enhancement Models to Pathological SpeakersNVIDIA · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Frame-Stacked Local Transformers for Efficient Multi-Codebook Speech GenerationNVIDIA · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Adaptive Per-Channel Energy Normalization Front-End for Robust Audio Signal ProcessingAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21VStyle: A Benchmark for Voice Style Adaptation with Spoken InstructionsAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21CARE: Cognitive-Reasoning Augmented Reinforcement for Emotional Support ConversationAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Fine-Tuning Large Multimodal Models for Automatic Pronunciation AssessmentMicrosoft · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Direct Simultaneous Translation Activation for Large Audio-Language ModelsAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21GUI-ARP: Enhancing Grounding with Adaptive Region Perception for GUI AgentsAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21