ETRI-Knowledge Sharing Plaform

Sound Quality Convolution Neural Network(CNN) Conventional Methods Speech Codec Spatial Audio Generative Models Coding Efficiency Deep Neural Network(DNN) Performance Evaluation Source Separation Speech Signals Sound Event Detection(SED) Network-Based Subjective Evaluation Multichannel Signals Stereo Audio Coding Method Sound Events Separation Performance Sequential Data Novel Method Activity Detection Research And Development Audio Information Audio Data Audio Signal Processing Adaptive Structure Architecture Model Bit Allocation Commercial Application Coding Gain Detection And Classification Data Shortage Data Compression Distortion Ratio Emotional Speech Frame-Level Feature Space Analysis High-Level Feature Media Content Modified Discrete Cosine Transform(MDCT) Millimeter Wave(mmWave) Speech Coding System Perceptual Similarity Receptive Field Audio Analysis Audio Features Adversarial Training Digital Media Enhanced Structure Event Localization Feature Prediction High-Dimensional High-Quality Large-Scale Detection Low Bit Rate Root Mean Square(RMS) Subjective Listening Tests Semi-Supervised Prior Information Quantization Error Unified Speech And Audio Coding(USAC) Waveform Synthesis Spectral Domain Speech Emotion Recognition Objective Evaluation Objective Assessment Data Correlation Deep Learning(DL) Extraction Method Frequency Domain(FD) Feature Learning Feature Transformation Feature Sequence Highly Efficient Model Compression Machine Learning Multi-Level State-Of-The-Art Speech Features User Experience Video Service Acoustic Data Audio Synthesis Automatic Music Transcription(AMT) Augmentation Method Basic Media Broadband Wireless Coding Scheme Compression Efficiency Events Detection Generative Adversarial Network Interactive Services Linear Prediction Latent Space Multichannel Audio Spectral Coefficients Spectral Characteristics Pitch Information Speech Database Neural Network Structure New Method Object-Based Reconstruction Performance Recovery Process Audio Generation Adaptive Pattern Baseline System Classification Method Compact Features Event Class Flow Factor Learning Algorithms Live Concert Real-World Speaker Embeddings S Characteristics Superior Performance Sinusoidal Vibration Pattern Recognition Perceptual Evaluation Of Speech Quality Waveform Reconstruction Analysis And Synthesis Bidirectional Recurrent Neural Network Computational Efficiency Detection Method Data Processing End-To-End Learning High Reality Imt-Advanced System Low Latency Music Recognition Model Complexity Siamese Network Spectral Components Stereo Coding Learning Methods Perceptual Speech Quality Perceptual Quality Proposed Model Optimal Transformation Audio Signal Compression Based Approach Computer Vision(CV) Data Augmentation Gated Recurrent Unit Hearing Impaired People Speech Characteristics Strict Causality Subjective Test Spatial Cue Musical Rhythm User Interface Vibration Signal Tactile Device Weakly Labeled Data Objective Test Attention Model Temporal Noise Shaping Residual Coding Audio Compression Convolutional Auto-Encoder Domestic Environment Deep Architecture Data Size Mobile Station(MS) Recognition Performance Signal Reconstruction Spectral Data Signal Processing Techniques Speaker Recognition Wireless Transmission