ETRI-Knowledge Sharing Plaform

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