ETRI-Knowledge Sharing Plaform

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