ETRI-Knowledge Sharing Plaform

Self-Improving Artificial Intelligence System Reduction Rate End-To-End Speech Recognition Error Reduction Training Data Recognition Model Automatic Speech Recognition(ASR) Speech Corpus Over Time Spontaneous Speech Korean Language Large Vocabulary Continuous Speech Recognition(LVCSR) Performance Levels Adaptive Parameter Deep Neural Network(DNN) Translation Model Speaker Adaptation Matrix Decomposition Limited Data Target Domain Online Services Open-Domain Dialog Text Normalization Data Scarcity Open Data Conventional Methods Large-Scale Performance Degradation Matching Pattern Transformation Method Machine Translation(MT) Korean Speech And Phrases Lm Adaptation Model Performance Model-Based New Method Post-Processing Clean Environment Code-Switching Computationally Expensive Translation Errors Deep Learning(DL) Language Model Adaptation Recognition Performance Affine Transformation Singular Value Decomposition(SVD) Correction Rate Automatic Conversion Linear Transformation Automatic Translation Need For