ETRI-Knowledge Sharing Plaform

Acoustic Model Deep Neural Network(DNN) Automatic Speech Recognition(ASR) Self-Improving Korean Speech Error Rate Speech Recognition System Speech Database Artificial Intelligence System Beam Search Signal Noise Ratio(SNR) Real-World Data Data Augmentation Robust Speech Recognition Based System State-Of-The-Art Speech Features Deep Learning(DL) Connectionist Temporal Classification(CTC) Transformer-Based Noisy Environments Bidirectional Lstm Objective Function Parameter Reduction Response Latency Real-Time Inference Raspberry Pi Audio Data Audiovisual Dataset Assessment Method Augmentation Techniques Average Latency Barrier-Free Conversational Speech Recognition Car Navigation System Context-Sensitive Enhancement Techniques Endpoint Detection Algorithm Hierarchical Detection GMM-HMM Human-Robot Interface High Accuracy Low-Resource Low-Power Model Structure Nonlinear Manifold Performance Improvement Performance Improved Viterbi Decoding Training Model Truncated Singular Value Decomposition Need For Automatic Translation Direct Detection Decision Fusion Error Reduction Embedded Device Gaussian Mixture Model(GMM) High Performance Localization Method Large Vocabulary Model Parameter Multiple Speakers Real Environment Server-Client Spectral Ratio Speech Recognition Accuracy User-Perceived Latency Signal-To-Noise Real-World Applications Blind Source Separation(BSS) Cross-Modality End-To-End Speech Recognition Field Environment Limited Resources Long Sequence Real-Time Operation Room Acoustic Reduction Technique Linear Regression Part Of Speech(POS) Post-Processing Method Voice Activity Detector Non-Stationary Noise Recognition Method Augmentation Method Audio Signal Detection Accuracy Efficient Algorithms Fine-Tuning Factorization Approach Hidden Markov Model Korean Language Computing Technology Robot System Speech Enhancement Search Task Separation Device Network-Based Optimized Model Overlapped Speech Detection Baseline System Channel Selection Frame Skipping Frequency Range Localization Algorithm Matrix Factorization Manifold Structure Mobile Application(APP) Phone Recognition Proficiency Assessment Web Speech Online Speech Recognition Recognition Model Art Performance Edge Devices Far-Field Formant Frequencies Low-Rank Matrix Low Latency Learning Methods Self-Supervised Learning Spectral Envelope Sound Source Localization Automatic Speech Recognizer Based Approach Transformer Model Acoustic Features Bidirectional Long Short-Term Memory Current State Digital Signal Processing Euclidean Norm Learning-Based Reduction Rate System Accuracy Voice Search Target Matrix Noise Separation Non-Native Speakers Overall Performance Time Factor Recognition Performance Audio And Video Confidence Measure Continuous Speech Computation Method Computational Complexity Cognitive Computing Iot Systems Log Data Language Barrier Manifold Regularized Mobile Speech Recognition Speech Feature Extraction Short Message