ETRI-Knowledge Sharing Plaform

Acoustic Model Self-Improving Compensation Method Artificial Intelligence System Support Vectormachine(SVM) Log Likelihood Ratio(LLR) Confidence Measure Word-Level Isolated Word Recognition Frame-Level Low-Resource Low Correlation Barrier-Free Embedded Devices Nonlinear Manifold Objective Function Within-Class Covariance Normalization Truncated Singular Value Decomposition Parameter Reduction Universal Background Model Model Parameter Automatic Translation Distance Method Non-Native Speech Position Information Similar Words Distance Algorithm Equal Error Rate Training Data Reduction Technique Vector Based Factorization Approach Channel Effect Correct Position Computing Technology Robust Speech Recognition Speech Recognition System System Performance I-Vector Linear Discriminant Analysis(LDA) Matrix Factorization Manifold Structure Cosine Distance Channel Compensation Deep Neural Network(DNN) Total Variability Phone Recognition Frequency Ratio Low-Rank Matrix Best Performance Distance Measure Non-Similar Word Similarity Knowledge-Based Acoustic Features Euclidean Norm Target Matrix Language Barrier Manifold Regularized Computational Complexity Cognitive Computing Relative Reduction