Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Scaling Bioacoustic Signal Pre-training with Million Samples Via Mask-ModelingiFlytek · IEEE International Conference on Acoustics Speech and Signal Processing3 citationsMar 12, 2025Self-supervised Prosody Learning at Phoneme-level with Momentum Contrast for Speech SynthesisiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025Leveraging Boolean Directivity Embedding for Binaural Target Speaker ExtractioniFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025Adversarial Speech-Text Pre-Training for Speech TranslationiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025Semi-Supervised Multilingual Alignment with Lexical Memory for Massively Parallel Text MiningiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025Anchored Monotonic Alignment and Representation Substitution for Rare Spontaneous Behaviors in Spontaneous Speech SynthesisiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025MixPro: Simple yet Effective Data Augmentation for Prompt-based LearningiFlytek · International Journal of Machine Learning and Cybernetics2 citationsFeb 27, 2025Beam pattern optimization using Pareto-enhanced particle swarm with cross-variance optimization (PPS-CVO) algorithmiFlytek · International Computational Imaging Conference (CITA)Feb 25, 2025A SURVIVAL ANALYSIS AND GRADE PREDICTION MODEL FOR LUNG SQUAMOUS CELL CARCINOMA BASED ON MULTIPLE-INSTANCE LEARNING AND MULTI-SCALE TRANSFORMERiFlytek · Journal of Mechanics in Medicine and BiologyFeb 21, 2025Lightweight Audio-Visual Wake Word Spotting With Diverse Acoustic Knowledge DistillationiFlytek · IEEE Transactions on Circuits and Systems for Video Technology5 citationsFeb 13, 2025MIH-TCCT: Mitigating Inconsistent Hallucinations in LLMs via Event-Driven Text-Code Cyclic TrainingiFlytek · arXiv (Cornell University)Feb 13, 2025Audio-visual representation learning via knowledge distillation from speech foundation modelsiFlytek · Pattern Recognition14 citationsFeb 12, 2025Target speaker lipreading by audio–visual self-distillation pretraining and speaker adaptationiFlytek · Expert Systems with Applications5 citationsFeb 8, 2025Towards Scene-Centric Multi-Level Interest Mining for Video RecommendationiFlytek · ACM Transactions on Multimedia Computing Communications and Applications2 citationsJan 23, 2025Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced OptimizationiFlytek · arXiv (Cornell University)Jan 23, 2025PhonemeVec: A Phoneme-Level Contextual Prosody Representation For Speech SynthesisiFlytek · ACM Transactions on Asian and Low-Resource Language Information Processing1 citationJan 15, 2025Skeleton and Font Generation Network for Zero-shot Chinese Character GenerationiFlytek · arXiv (Cornell University)Jan 14, 2025Gogglesdet: goggles detection with clustering transformer and a new datasetiFlytek · Signal Image and Video ProcessingJan 3, 2025MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task LearningiFlytek · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)10 citationsJan 1, 2025Imprints: Mitigating Watermark Removal Attacks With Defensive WatermarksiFlytek · IEEE Transactions on Information Forensics and Security9 citationsJan 1, 2025Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question AnsweringiFlytek · Annual Meeting of the Association for Computational Linguistics (ACL)7 citationsJan 1, 2025DCF-DS: Deep Cascade Fusion of Diarization and Separation for Speech Recognition Under Realistic Single-Channel ConditionsiFlytek · IEEE Transactions on Audio Speech and Language Processing5 citationsJan 1, 2025Voice Attribute Editing With Text PromptiFlytek · IEEE Transactions on Audio Speech and Language Processing5 citationsJan 1, 2025SCITAT: A Question Answering Benchmark for Scientific Tables and Text Covering Diverse Reasoning TypesiFlytek · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)4 citationsJan 1, 2025Bridged Semantic Alignment for Zero-Shot 3D Medical Image DiagnosisiFlytek · IEEE Journal of Biomedical and Health Informatics3 citationsJan 1, 2025