ETRI-Knowledge Sharing Plaform

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