ETRI-Knowledge Sharing Plaform

Model Parameter Speech Signals Speech Recognition System Automatic Speech Recognition(ASR) Self-Improving Data Augmentation Acoustic Features Artificial Intelligence System Car Navigation System Wall Street Convolution Neural Network(CNN) Reduction Technique Feature Vector Phone Recognition Training Data CD-DNN-HMM Input Features Parameter Reduction Phone Error Rate Student Learning Conversion Model Bidirectional Lstm Taylor Series Word Error Rate Deep Learning(DL) Speech Features Korean Speech Weight Matrix Semi-Supervised Training Compensation Method Target Domain Large-Scale Network-Based Performance Degradation Speech Database Spontaneous Speech Learning Methods Dnn-Based Acoustic Model Training Process Spectral Features Confidence Measure Computational Complexity Training Based Assessment Method Augmentation Techniques Conversational Speech Recognition Channel Normalization Context-Sensitive Data-Driven Approach Discriminative Information Barrier-Free Behavior Strategy Truncated Singular Value Decomposition Universal Background Model Viterbi Decoding Speech-To-Text(STT) Linear Separability Within-Class Covariance Normalization Embedded Devices Frequency Filtering Filtering Method Graph Regularized High Accuracy Healthy Controls Low-Resource Linear Structure Maximum A Posteriori Map-Based Multiple Domains Native Language Nonlinear Manifold Objective Function Performance Improvement Priori Signal-To-Noise Ratio Polynomial Expansion Pattern Extraction Paired Data Response Latency Raw Data Spoken Language Understanding Single Parameter Shared Task Sequential Data Smartphone-Based Second Language Signal Characteristics Automatic Translation Cost Function Batch Processing Text-Dependent User-Perceived Latency Unlabeled Samples Error Reduction Educational Use High Performance Image Recognition Language Modeling Large Vocabulary Mental Illness Noisy Environments Policy Gradient Method Qualitative Characteristics Reduced Model Server-Client Speech Generation Self-Training Source Domain Speech Recognition Accuracy Classification Error Conversion Method Connectionist Temporal Classification(CTC) Data Sets Training Method Transformer-Based Transfer Learning Vector Based Unlabeled Data Voice Activity Detector Word-Level English Sentence Feedforward Neural Networks Feed-Forward Deep Neural Network Handwritten Digit Recognition Hmm Based Speech Recognition Isolated Word Recognition Language Learning Learning Process Linear Regression Language Generation Limited Resources Long Sequence Major Depressive Disorder(MDD) N-Gram Neural Network Approach Post-Processing Method Pre-Trained Model Spectral Domain Real-World Applications Scoring Model State-Of-The-Art Speech Modeling Channel Effect Computing Technology Diagonal Matrix Depressive Disorders External Knowledge Error Back-Propagation Factorization Approach Generative Adversarial Network Higher Performance High-Dimensional Features Intelligent Robot Local Patches Korean Language Low-Rank Matrix Approximation Linguistic Content Machine Learning Models Noise Components Prior Knowledge Real-Time Random Selection Speech Quality Speech Synthesis Sound Quality Speech Translation Total Variability Active Learning Method Acoustic Characteristics Auxiliary Networks Acoustic Model Training Cosine Distance Channel Compensation Cross-Entropy Classification Accuracy Decision-Directed Approach Beam Search Band-Pass Filter(BPF) Temporal Context Linguistic Information Feature Extraction Method Feature Normalization Graph-Based Approach Frame Skipping Human Knowledge I-Vector Linear Discriminant Analysis(LDA) Learning System Language Learners Latent Variable Loss Function Learning Based Approach Learning Algorithms Learning Network Latent Semantic Analysis(LSI) Matrix Factorization Manifold Structure Mel-Frequency Cepstrum Coefficients(MFCC) Output Snr Proficiency Assessment Proficiency Evaluation Single-Channel Speech Enhancement Signal Noise Ratio(SNR) Read Speech Recurrent Neural Network(RNN) Spectral Peaks Support Vectormachine(SVM) Signal Processing Speech Assessment Superior Performance Speaker Conversion Answer Extraction Acoustic Properties Accuracy Improvement Art Performance Data Sparseness Best Performance Backpropagation Algorithm Deep Convolutional Neural Networks Entropy Loss Engineering Approach Finite State Integrated System Low Latency Latent Semantics L1 And L2-Norm Mental Health Treatment Many-To-Many Nonlinear Activation Function Nonlinear Input Online Speech Recognition Piecewise Linear Phase Information Proposed Model Pseudo Labels Quiz Game Style Conversion Self-Supervised Learning Speaker Similarity Adaptive Modulation Automatic Speech Recognizer Case Studies Chain Based Bidirectional Long Short-Term Memory Training Cycle Time-Domain Target Matrix Test Set Word Segmentation Window Size Euclidean Norm Frequency Cepstral Coefficients Channel Noise Local Linear Machine Learning Technique(MLT) Magnitude And Phase Minimum Mean Square Error(MMSE) Nonlinear Function Normalization Method Peaks And Valleys Phase-Based Pronunciation Evaluation Posterior Probability Estimation Performance Gain Parameter Optimization Research Topics Reduction Rate Reinforcement Learning Algorithm Speech Information System Accuracy Stable Model Automatic Diagnosis Automatic Identification Computation Method Cognitive Computing Cnn Model Depression Detection Differential Diagnosis Text-Based End To End(E2E) Frame Delay Generation Process Feature Construction Classification Performance Linear Interpolation Local Minima Language Barrier Manifold Regularized Modulation Frequency Non-Native Speakers Noisy Speech Priori Snr Parameter Space Quality Enhancement Question Answering Recognition Performance Rank Selection Second-Order Sparsity Constraint Speech Feature Extraction