ETRI-Knowledge Sharing Plaform

Self-Improving Artificial Intelligence System Multi-Agent Reinforcement Learning Speech Signals Dialog System ITU-T Telepresence System Sound Quality State-Of-The-Art Word Embedding Models Model-Based Transmission Gate(TG) Acoustic Echo Cancellation Bit Allocation Data-Driven Voice Activity Detection(VAD) Estimation Technique Feature Compensation High Accuracy Item Recommendation Multi-Item Multiple Domains Partitioned Block Frequency Domain Conversion Model Predator-Prey Efficient Exploration Encoding Technique High Definition Multi-Agent System(MAS) New Algorithm Novel Approach Noisy Environments Post-Processing Sub-Band Source Domain Conversion Method Conditional Mutual Information Different Levels Multiple Models Natural Gradient Network Time Protocol(NTP) N-Gram Skip-Gram Speech Modeling Audio Signal Automatic Evaluation Computing Technology Complex Dynamics Embedding Method Generative Adversarial Network High Dimension Input Signal Linguistic Content Robust Speech Recognition Speech Quality Speech Communication Based Prioritization Target Domain Explore Action Learning Network Learning Algorithms Large-Scale Performance Analysis Relative Position Spectral Peaks Short-Term Starcraft Ii Speaker Conversion Audio Recording Decision Making Thought Model Value Function Execution Framework Interacting Multiple Model(IMM) Inter-Frame Correlation Many-To-Many Piecewise Linear Spectral Envelope Sentence Model Sentence Similarity Style Conversion Self-Supervised Learning Speaker Similarity Analytical Approach Context Model Clustering-Based Joint Action User Equipment(UE) Frequency Domain Adaptive Filter Imm Algorithm Kullback-Leibler (Kl) Divergence Learning Curve Peaks And Valleys Reduction Rate Spectral Subtraction(SS) Spectral Features Stable Model Time Synchronization Allocation Strategy Action Selection Cognitive Computing Variable Step Size Embedding Technique Linear Interpolation Local Minima Quality Enhancement Simulation Results Soft-Decision