Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Combining SSL Speech Features, Contextual Transformers and Mamba Models for Realistic Audio Spoofing DetectionMicrosoft · IEEE International Conference on Acoustics Speech and Signal Processing1 citationApr 21FW-VTON: Flattening-and-Warping for Person-to-Person Virtual Try-OnAlibaba · IEEE International Conference on Acoustics Speech and Signal Processing1 citationApr 21Train Short, Infer Long: Speech-LLM Enables Zero-Shot Streamable Joint ASR and Diarization on Long AudioMicrosoft · IEEE International Conference on Acoustics Speech and Signal Processing1 citationApr 21Group Relative Policy Optimization for Text-to-Speech with Large Language ModelsiFlytek · IEEE International Conference on Acoustics Speech and Signal Processing1 citationApr 21Towards Real-Time Generative Speech Restoration with Flow-MatchingMicrosoft · IEEE International Conference on Acoustics Speech and Signal Processing1 citationApr 21pTSE-T: Presentation Target Speaker Extraction Using Unaligned Text CuesAlibaba · IEEE International Conference on Acoustics Speech and Signal Processing1 citationApr 21AgenticRecTune: Multi-Agent with Self-Evolving Skillhub for Recommendation System OptimizationAlphabet · arXiv (Cornell University)Apr 21Reasoning-Aware AIGC Detection via Alignment and ReinforcementMicrosoft · arXiv (Cornell University)Apr 21How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative ReasoningAlibaba · arXiv (Cornell University)Apr 21Direct U(2) approximation via repeat-until-success circuitsMicrosoft · arXiv (Cornell University)Apr 21Continuous Semantic Caching for Low-Cost LLM ServingMicrosoft · arXiv (Cornell University)Apr 21TEMPO: Scaling Test-time Training for Large Reasoning ModelsAlibaba · arXiv (Cornell University)Apr 21LoopCTR: Unlocking the Loop Scaling Power for Click-Through Rate PredictionAlibaba · arXiv (Cornell University)Apr 21Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency RegularizationNVIDIA · arXiv (Cornell University)Apr 21Thinking Before Matching: A Reinforcement Reasoning Paradigm Towards General Person Re-IdentificationAlibaba · arXiv (Cornell University)Apr 21CulturALL: Benchmarking Multilingual and Multicultural Competence of LLMs on Grounded TasksAlibaba · arXiv (Cornell University)Apr 21UAF: A Unified Audio Front-end LLM for Full-Duplex Speech InteractionAlibaba · arXiv (Cornell University)Apr 21How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative ReasoningAlibaba · arXiv (Cornell University)Apr 21Reasoning-Aware AIGC Detection via Alignment and ReinforcementMicrosoft · arXiv (Cornell University)Apr 21A Simple Communication Scheme for Distributed Fast Multipole MethodsGraphcore · arXiv (Cornell University)Apr 21E2E-AEC: Implementing An End-To-End Neural Network Learning Approach for Acoustic Echo CancellationAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Scalable Information Leakage Detection in IoT web InterfacesMoore Threads · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21CIF: A Two-Stage Cognitively-Inspired Framework for Chinese Spelling CorrectioniFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Distilling Attention Knowledge for Speaker VerificationMicrosoft · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21SLM-TTA: A Framework for Test-Time Adaptation of Generative Spoken Language ModelsMeta · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21