ETRI-Knowledge Sharing Plaform

Spontaneous Speech Data Augmentation Learning Methods Self-Improving Transfer Learning Artificial Intelligence System CD-DNN-HMM Sub-Models Wiener Filter Speech Recognition Accuracy Language Learning Noise-Robust Model-Based Statistical Model Conventional Methods Learning System New Method Automatic Speech Recognition(ASR) Active Learning Method Proficiency Evaluation Processing Method Speech Analysis Speech Database Speaking Style Speech Assessment Signal Processing Tutoring System Semi-Supervised Learning Method Target Domain Car Interior Computational Efficiency Computational Cost Convergence Time Computer Simulation(MC and MD) Acoustic Properties Disease Recognition Engineering Approach Hidden Nodes Integrated System Large Vocabulary Continuous Speech Recognition Point Of Interest Resource-Constrained Speech Signals Sub-Frame Dynamic Features Dnn-Based Acoustic Model End-To-End Asr Performance Gain Spectrum Analyzer Temporal Dynamics Voice Recognition Car Navigation Computational Complexity Alzheimer'S Disease(AD) Cognitive Computing Error Analysis Empirical Study Linear Interpolation Language Barrier Recognition Performance Barrier-Free Dynamic Characteristics Data-Driven Approach Filter Estimation Foreign Speech Wall Street Multi-Condition Training Noise Adaptive Training Performance Improvement Reconstruction Method Spoken Language Understanding Student Learning Speech Recognizers Automatic Translation Frame Rate Gaussian Mixture Model(GMM) Word Error Rate Navigation System Qualitative Characteristics Spectral Changes Relative Performance Spectrum Reconstruction Self-Training Two-Stage Training Method Deep Learning(DL) Hmm Based Speech Recognition Learning Process Log-Likelihood Multi-Style Training Noise Reduction(NR) Noise Suppression Spectral Fluctuations Soft Masking Semi-Supervised Training Training Data Transformer-Based Voice Data Double-Delta Distributed Speech Recognition(DSR) Computing Technology Hidden Markov Model Inter-Frame Language Model Non-Stationary Robust Speech Recognition Signal Distortion Random Selection Speech Recognition System Unified Approach Deep Neural Network(DNN) Environment Noise Feature Extraction Method Latent Variable Multi-Set