ETRI-Knowledge Sharing Plaform

Model Parameter Deep Neural Network(DNN) Acoustic Features Speech Signal Speech Corpora Statistical Model End Point Detection(EPD) Model-Based Robust Speech Recognition Finite State Transducer Phone Recognition Statistical Hypothesis Testing Decision Knowledge Dnn-Based Acoustic Model Knowledge-Based Non-Speech Computational Complexity Failure Rate Feature Vector Cascaded Decision Decision Parameters Decision Logic Convolution Neural Network(CNN) Unified Framework Taylor Series Two-Stage Speech Recognition Accuracy CD-DNN-HMM Frame-Level Wall Street Truncated Singular Value Decomposition Emotional Speech Behavior Strategy Barrier-Free Car Body Car Navigation System Dynamic Characteristics Embedded Devices Filter Estimation Graph Regularized Human-Robot Interface Impact Noise Linear Structure Linear Separability Low-Resource Nonlinear Manifold Objective Function Parameter Reduction Phone Error Rate Polynomial Expansion Reconstruction Method Raw Data Speech Classification Student Learning Automatic Translation Word Error Rate Wiener Filter Unlabeled Samples Cost Function Error Reduction Localization Method Large Vocabulary Mechanical Sensing Post-Processing Policy Gradient Method Spectrum Reconstruction Spectral Changes Speech Generation Self-Training Source Domain Room Acoustic Spectral Fluctuations Speech Corpus Weight Matrix Background Noise Blind Source Separation(BSS) Training Method Unlabeled Data Feedforward Neural Networks Handwritten Digit Recognition Hmm Based Speech Recognition Noise Reduction(NR) Noise Suppression Pre-Trained Model Reduction Technique Real-Time Operation Service Performance Signal-To-Noise Semi-Supervised Training Speech Emotion Recognition Scoring Model Unsupervised Domain Adaptation Double-Delta Distributed Speech Recognition(DSR) Error Back-Propagation External Knowledge Factorization Approach Hidden Markov Model High-Dimensional Features Input Signal Inter-Frame Non-Stationary Noise Prior Knowledge Robot System Signal Distortion Separation Device Speech Recognition System Acoustic Model Training Artificial Intelligence System Target Domain Conventional Methods Channel Selection Feature Extraction Method Graph-Based Approach Human Knowledge Localization Algorithm Learning Algorithms Matrix Factorization Manifold Structure Processing Method Signal Detector Similarity Information Speech Analysis Spontaneous Speech Automatic Speech Recognition(ASR) Backpropagation Algorithm Voice Command Car Interior Computational Efficiency Computational Cost Data-Driven Learning Engineering Approach Learning Methods L1 And L2-Norm Low-Rank Matrix Nonlinear Activation Function Nonlinear Input Pseudo Labels Resource-Constrained Sub-Frame Sound Source Localization Automatic Speech Recognizer Spectrum Analyzer Temporal Dynamics Time-Domain Test Set Dynamic Features Parameter Optimization Training Process Training Cycle Data Augmentation Digital Signal Processing Euclidean Norm Local Linear Likelihood Ratio Test Nonlinear Function Probabilistic Decision Posterior Probability Estimation Performance Gain Road Condition Reinforcement Learning Algorithm Reduction Rate Speech Recordings Target Matrix Self-Improving Time-Scale Modification(TSM) Voice Recognition Vehicle Body Computational Auditory Scene Analysis Cross-Corpus Confidence Measure Degraded Service Generation Process Input Features Language Barrier Manifold Regularized Noise Separation Parameter Space Recognition Performance