ETRI-Knowledge Sharing Plaform

Automatic Translation Barrier-Free Language Barrier Self-Improving Artificial Intelligence System Preliminary Study Reduction Rate Model-Based N-Gram Translation Model Speech Recognition System Text Corpus Deep Neural Network(DNN) Model Parameter Acoustic Model Automatic Speech Recognition(ASR) Multi-Domain Decision Tree(DT) Speech-To-Speech Translation System Error Reduction Mobile Devices Basic Functions Cepstral Features Diagnosis System Excellent Performance Filtering Process Energy Operator Neural Machine Translation Online Services Performance Levels Search Results Linear Transformation Convolution Neural Network(CNN) Gradient Boosting High-Quality Speech Recognition Technology Simple Structure Two-Stage User-Friendly User Satisfaction Adaptive Parameter Code-Switching Divergence Measure Contextual Information Construction Procedure Data Sets European Languages End Point Detection(EPD) End-To-End Speech Recognition Freely Available Higher-Order Statistics Korean Speech Lattice Network Minimum Description Length (Mdl) Criterion Machine Learning Matrix Decomposition Parallel Data Structured Classification Speaker Adaptation Speech Corpus Text-To-Speech(TTS) Tree-Based Training Data Technology Infrastructure Time Information Deep Learning(DL) Arabic Speech Recognition Break Prediction Break Strength Classification Algorithm Feature Set Hidden Markov Model Infrastructure Support Markov Process Prior Knowledge Robust Speech Recognition Speech Synthesis Ted Talks Voice Signal Baseline System Consumer Devices Classification Models Conventional Methods Large-Scale Linguistic Features Source Language New Method Open Technology Prediction Model Speech Database Singular Value Decomposition(SVD) Spontaneous Speech Transformation Method Target Domain Feature Extraction Method Large Vocabulary Speech Recognition Clean Environment Affine Transformation Computationally Expensive Distance Measure DNN-HMM Error Rate Large Vocabulary Continuous Speech Recognition Multi-Language Proposed Model Recognition Model Statistical Information Translation Technology Target Language Topic Model Zero-Crossing Government Open Data Kullback-Leibler (Kl) Divergence Lm Adaptation Medical Diagnosis Mobile System Non-Homogeneous Pathological Voice Sentence-Final Intonation Speech Act Speech Information Test Set Training Set F-Measure Multilingual Speech Chime Challenge Correction Rate Intelligent Vehicle Language Model Adaptation Mixture Components Optimization Methods Open-Domain Dialog Prediction Accuracy Quality Of Life Recognition Performance Speech Signal Text Data Total Cost Word Embedding