ETRI-Knowledge Sharing Plaform

Self-Improving Point Of Interest Artificial Intelligence System Automatic Speech Recognition(ASR) Robust Speech Recognition Model-Based Dialogue System Automatic Translation Language Barrier Multi-Stage Deep Learning(DL) Word Error Rate Deep Neural Network(DNN) Barrier-Free Maximum A Posteriori Endpoint Detection Second Language Learning Noisy Environments Computational Complexity Speech Signals Native Language Signal Noise Ratio(SNR) Recognition Performance Learning Methods Spontaneous Speech Speech Recognition Accuracy Bilinear Transformation Space Based Big-Data Minimum Classification Error Car Navigation System Prior Distribution Non-Speech Data Augmentation Frame-Level Performance Degradation Automatic Speech Recognizer Map-Based Task-Oriented Finite State Transducer Learning System Intermediate Input Statistical Model Speech Recognition System New Method Acoustic Model Noisy Speech Two-Stage Task Graph Efficient Computation Embedding Model Noise Reduction(NR) Cascaded Decision Direct Detection Magnitude And Phase Word Accuracy Spectral Domain Graph-Based Car Interior Fixed Point Non-Stationary Noise Quiz Game Impact Noise Stand-Alone Weak Points Output Snr Adaptation Strategies Knowledge Inference Noise Adaptive Training Enhancement Techniques Noise Separation Robot System Experimental Result Temporal Dynamics Hmm-Based Confidence Measure Dynamic Features Prior Model Accurate Estimation Driving Conditions Spectral Characteristics Voice Recognition Computer Assisted Language Learning Detection Error Car Body Human Interaction Incremental Learning Method Knowledge Expansion Memory Model Non-Native Speech Real-Time Operation Efficient Algorithms Computational Cost Decision Parameters Double-Delta Decoding Algorithm Ensemble Classifiers Early Fusion Long-Short Term Memory(LSTM) Reconstruction Method Speech Corpus Hybrid Approach Unified Framework Linear Regression Road Condition Isolated Word Learning Algorithm Hidden Markov Model(HMM) Management Model Priori Signal-To-Noise Ratio Real Environment Decoding Method Language Identification Latent Semantic Analysis Late Fusion Failure Rate Neural Network Model Dynamic Characteristics Digital Signal Processing Improving Accuracy Probabilistic Scheme Service Performance Speech Separation Processing Method Language Learners Linear Discriminant Analysis(LDA) Mechanical Sensing Spectral Fluctuations Spoken Dialog System Dimension Reduction Embedded Devices Pronunciation Evaluation Cognitive Computing Decision Logic On-Line Output Prediction Wiener Filter Data-Driven Approach Error Reduction Statistical Learning Background Noise Channel Selection Field Application Pattern Extraction Assessment System Reinforcement Learning(RL) Robust Recognition Spoken Language Understanding Small-Scale Text-Based Variance Function Minimum Mean Square Error(MMSE) Resource-Constrained Localization Algorithm Retail Market Service Model Feature Extraction Machine Learning Technique(MLT) Overall Performance Parameter Estimation Sub-Frame Separation Device Human Brain I-Vector Speech Classification Speech Corpora Spectrum Analyzer Speech Assessment Support Vectormachine(SVM) Count-Based Question Answering Decision-Directed Approach Voice Command Input Signal Frequency Range Speech Feature Vectors Text Data Acceptance Or Rejection Voice Search Viterbi Algorithm Spectral Envelope Word Segmentation Answer Extraction Computational Auditory Scene Analysis Probabilistic Decision Spectrum Reconstruction Target Environment Domain Adaptation Room Acoustic Spectral Ratio Tightly Coupled Unknown Data Conventional Methods Mobile Environment Phase Information Complex Modal Extraction Method Large-Scale Priori Snr Formant Frequencies Cooperative Learning English Proficiency History Management Network-Based Anaphora Resolution Noise Suppression Sound Source Localization Blind Source Separation(BSS) Educational Use Single-Channel Speech Enhancement Efficient Learning Goal-Oriented Large Vocabulary Degraded Service Grammatical Errors Search Task Assessment Method End-To-End Trainable Human-Robot Interface Vehicle Body Likelihood Ratio Test(LRT) Moving Vehicle Frame Delay Rule-Based Approach Small Set Discourse Context Filter Estimation New Type Phase-Based Time-Frequency Mask Speaking Skills Intelligent Robot Speech Recordings Computational Efficiency Compensation Method Computing Technology Knowledge-Based Optimal Weights Decision Knowledge Distributed Speech Recognition(DSR) Rule-Based System Speech Events Case Studies Reduction Rate Inter-Frame Front-End Intelligent Tutoring Latent Semantics Performance Gain Procedural Knowledge Speech Features Speech Synthesis Dialogue Management Language Modeling Spectral Changes Speech Analysis Localization Method Experiment Results N-Gram Lm Signal Distortion Statistical Hypothesis Testing Shared Task Baseline System