ETRI-Knowledge Sharing Plaform

Self-Improving Artificial Intelligence System Automatic Speech Recognition(ASR) Reduction Rate Deep Learning(DL) End-To-End Speech Recognition Training Data Speaker Adaptation Speech Corpus Machine Translation(MT) Matrix Decomposition Model-Based Open Data Conventional Methods Clean Environment Deep Neural Network(DNN) Transformation Method Target Domain Singular Value Decomposition(SVD) Spontaneous Speech Large-Scale New Method Affine Transformation Computationally Expensive Recognition Model Large Vocabulary Continuous Speech Recognition Lm Adaptation Correction Rate Recognition Performance Language Model Adaptation Code-Switching Adaptive Parameter Error Reduction Performance Levels Open-Domain Dialog Linear Transformation Online Services