ETRI-Knowledge Sharing Plaform

Model Parameter Deep Neural Network(DNN) End Point Detection(EPD) Computational Complexity Word Error Rate Acoustic Features Speech Signals Statistical Model Inter-Frame Model-Based Robust Speech Recognition Finite State Transducer Phone Recognition Automatic Speech Recognition(ASR) Point Of Interest Non-Speech Dnn-Based Acoustic Model Likelihood Ratio Test Performance Gain Recognition Performance Feature Vector Signal-To-Noise Speech Corpora Speech Corpus Taylor Series Speech Recognition Accuracy Front-End Convolution Neural Network(CNN) Two-Stage CD-DNN-HMM Wall Street Acoustic Source Objective Function Parameter Reduction Speech Classification Behavior Strategy Barrier-Free Car Body Conversational Speech Recognition Car Navigation System Dynamic Characteristics Detection Error Emotional Speech Frame-Level Filter Estimation Graph Regularized Human-Robot Interface Impact Noise Low-Resource Linear Structure Linear Separability Moving Vehicle Nonlinear Manifold Reconstruction Method Student Learning Raw Data Performance Improvement Phone Error Rate Polynomial Expansion Synchronization Procedure Truncated Singular Value Decomposition Unified Framework Speech Generation Normalized Cross-Correlation Automatic Translation Cepstral Coefficients Cross-Correlation Function(CCF) Computationally Efficient Cost Function Decision Logic Decision Parameters Embedded Device Error Reduction Localization Method Large Vocabulary Level-Crossing Mechanical Sensing Mobile Environment Self-Training Source Domain Spectrum Reconstruction Spatial Information Spectral Changes Post-Processing Policy Gradient Method Wiener Filter Unlabeled Samples Scoring Model Accurate Estimation Training Method Background Noise Blind Source Separation(BSS) Cascaded Decision Context-Dependent Estimation Method Feedforward Neural Networks Hmm Based Speech Recognition Handwritten Digit Recognition Korean Speech Noise Reduction(NR) Noise Suppression Real-Time Operation Room Acoustic Reduction Technique Semi-Supervised Training Speech Emotion Recognition Service Performance Spectral Fluctuations Pre-Trained Model Weight Matrix Unlabeled Data Non-Stationary Noise Speech Recognition System Compensation Method Double-Delta Distributed Speech Recognition(DSR) Error Back-Propagation External Knowledge Factorization Approach Hidden Markov Model High-Dimensional Features Input Signal Level Alignment Robot System Signal Distortion Signal Detection Prior Knowledge Unsupervised Domain Adaptation Separation Device Spectral Characteristics Speech Quality Target Location Performance Degradation Target Domain Acoustic Model Training Artificial Intelligence System Conventional Methods Channel Selection Feature Extraction Method Graph-Based Approach Human Knowledge Localization Algorithm Learning Algorithms Mel-Frequency Cepstrum Coefficients(MFCC) Matrix Factorization Manifold Structure Spontaneous Speech Signal Detector Similarity Information Signal Noise Ratio(SNR) Speech Analysis Processing Method Viterbi Algorithm Time-Frequency Mask Nonlinear Input Statistical Hypothesis Testing Back Propagation Algorithm Car Interior Computational Efficiency Computational Cost Data-Driven Learning Engineering Approach Isolated Word Low-Rank Matrix L1 And L2-Norm Learning Methods Microphone Arrays Nonlinear Activation Function Retail Market Resource-Constrained Speech Separation Sub-Frame Pseudo Labels Voice Command Zero-Crossing Sound Source Localization Synthesized Speech Training Process Training Cycle Time-Domain Test Set Reduction Rate Reinforcement Learning Algorithm Automatic Speech Recognizer Decision Knowledge Dynamic Features Data Augmentation Digital Signal Processing Driving Conditions Euclidean Norm Knowledge-Based Local Linear Nonlinear Function Road Condition Speech Recordings Spectrum Analyzer Probabilistic Decision Parameter Optimization Posterior Probability Estimation Subjective Preference Target Matrix Temporal Dynamics Noise Separation Time-Scale Modification(TSM) Computational Auditory Scene Analysis Confidence Measure Cross-Corpus Degraded Service Failure Rate Filter Bank Generation Process Input Features Language Barrier Manifold Regularized Noisy Speech Robust Recognition Parameter Space Vehicle Body Voice Recognition 3-Level Self-Improving Speech Events