ETRI-Knowledge Sharing Plaform

Sound Quality Mpeg Surround Deep Neural Network(DNN) Perceptual Quality Spatial Cue Psychoacoustic Model Speech Codec Spatial Audio Coding Loss Function MPEG-H Time-Domain Unified Speech And Audio Coding(USAC) Coding Scheme Source Location Light Field Low Bit Rate Speech Coding Performance Evaluation Audio Quality Linear Predictive Coding Digital Radio Temporal Noise Shaping Immersive Audio AMR-WB Modified Discrete Cosine Transform(MDCT) Location Information Convolution Neural Network(CNN) Side Information Subjective Assessment Coding Performance Superior Performance Complex-Valued Virtual Source Speech Coder Audio Codec Stereo Audio Multi Time Scale Quantization Noise Single Mode Entropy Model 3d Audio Compact Representation Coding Method Objective Metrics Reference Model Coding Efficiency Multichannel Signals Generative Models Model Complexity Transient Signal Compression Performance Level Difference MPEG-I Subjective Listening Tests New Method Subjective Test Compression Method Compression Techniques Digital Cinema Distortion Measure Signal Noise Ratio(SNR) Frequency Band Coding System Two-Dimensional(2D) Data Rate Audio Data Realistic Broadcasting Wide Range State-Of-The-Art Sub-Networks Multiple Sources Coded Excitation Additional Information High Performance Entropy Coding Scale-Up Perceptual Optimization Residual Learning Subjective Evaluation Acoustic Channel Digital Multimedia Broadcasting Pre-Echo Digital Signage Acoustic Data Transmission Service System Intelligent Analysis Conventional Methods Multi-Scale Noisy Environments Residual Signal Arithmetic Coding Network-Based Data Base Transmission System Technology Infrastructure Speech Compression Basic Media Spectral Coefficients Speech Signals Broadcasting System Encoder And Decoder Media Streaming Multi-Resolution Bit Allocation Cross-Module Speech Features Sound Source Multiple Context Proposed Model Coding Algorithm Gradient Histogram Gradient Method Noise Model Optimization Techniques Partial Discharge(P.D) Gas Leakage Uniform Quantization Word Recognition Adaptive Structure Based Approach Distortion Ratio Transform Domain Switching System Frequency Regions Computational Efficiency Interactive Music Highly Efficient Lapped Transform Digital Audio Broadcasting Generative Adversarial Network Perceptual Evaluation Of Speech Quality Selection Method Interactive Services Quality Improvement Side Effects Separation Module Coding Artifacts Memory Requirements Perceptual Transparency Perceptual Similarity Frequency Dependent Model Compression Subband Analysis Audio Encoding Blocking Effect Generation Technology Massive Data Machine Learning Based Noise Spectra Optimization Performance Training Data Weighted Histogram Cbs Algorithm High Efficiency Advanced Audio Coding Representation Method Warped Linear Prediction Convolution Operation Noisy Speech Neural Network Structure Post-Processing Audio Cues Intrinsic Information Lossless Compression Data Correlation Separation Algorithm Permutation Ambiguity Quantization Process Spectral Information MPEG-2 TS Public Datasets Clean Speech Quantization Method Approximation Model And Virtual Reality Blind Deconvolution Uniform Noise Speech Source Scalable Architecture Adaptive Pattern Extraction Method Linear Prediction Analysis Training Method Separation Performance Blind Separation Intelligent Multimedia Next-Generation Multi-Standard Quantization Error Sample Density Broadband Wireless Divisive Normalization Digital Media Feature Representation Virtual Reality Applications Video Compression Siamese Network Speaker Embeddings Blind Source Separation(BSS) Compatibility Test Design And Development Image Compression Test Code Unrestricted Polar Quantization Multiview Video Respiratory Sound(RS) Second Order Statistics(SOS) Spectral Data Sound Classification Wireless Transmission Encoding And Decoding Overlap-Add Optimization Methods Test Equipment Transmission Technology Spatial Audio Object Coding Feature Transformation Objective Test Performance Improvement Stereo Sound Stereo Coding Commercial Application End-To-End Learning Skip Connections Parametric Coding Quality Level Short Time Fourier Transform Coding Gain Latent Space Millimeter Wave(mmWave) Objective Evaluation Temporal Resolution Version 2 Spectral Components Sequential Information Information Flow Mode Of Operation New Approach Probability Distribution Pre-Processing Minimal Energy Noisy Conditions Time-Frequency Representation ATSC 3.0 LDM Dft Coefficients Network Architecture Phase Shift Keying Transition Control Transient Periods Switching Operation Convolutive Source Separation Feature Extraction High-Dimensional Multichannel Audio Compression Switching Scheme Backward Compatible Complex Architecture Digital Signal Processing Methods Latent Embeddings Stochastic Noise Arithmetic Coder Context Adaptive Peak-Signal-To-Noise-Ratio(PSNR) Compression Rate Narrow Bandwidth Convolutive Mixtures Model Structure Memory Usage Need For Phase Contrast Input Signal Automatic Speech Recognition(ASR) Compression Problem Complex Values Perceived Quality Extraction Technique Local Gradient(LG) Augmentation Method Discrete Fourier Transform Function Design In-Between Coding Techniques Flow Factor Model Components Video Coding Standard Algorithmic Delay Multi-Level Optimal Transformation Control Algorithm Domain-Specific Hybrid Design Network Bandwidth Perceptual Speech Quality Angle-Based Decoding Complexity Wide Frequency Range Wide Band Codebook Search Real-Time Real-Valued Coding Visual Quality Subjective Quality Evaluation System Integrated Computational Capacity Mobile Station(MS) Residual Network Recognition Accuracy Speech Characteristics Audio Objects High-Quality Memory Reduction Relative Gradient Non-Parametric Time Encoding Bit Overhead Neural Network Model Open Technology Prior Information Dynamic Characteristics Lossless Coding Two-Phase Transform Coding Advanced Technology Speech Separation Joint Diagonalization Mel-Frequency Optimization Process Classification Performance Transmission Method Sound Waves Compact Model High Frequency(HF) Prediction And Analysis Structure Similarity Index Measure(SSIM) Indirect Measurement Scale-Down Backward Compatibility Infrastructure Support Dimensionality Reduction Methods Entropy-Based End System Inserting Zeros Mean Square Error(MSE) Coding Models Time-Frequency Domain Lp Residual Magnitude Information Data Transfer Large Numbers Two-Stage Weighting Scheme S Characteristics Acoustic Features Long-Term Dependencies Memory Consumption Spatial Image High Compression Ratio Input Data Main Network Recovery Process Training Scheme Quantization Levels Adversarial Training Context Modeling Data Compression Frequency Domain Signal Intermediate Complex Low Bit Error Rate Objective Assessment Two Dimensions Low Delay Mpeg-4 Noise Robust Feature Visualization Tool Spectral Band Replication(SBR) Consistent Quality Experimental Result Estimation Performance Masking Threshold Object-Based Audio Compression Efficiency Video Service Attention Model Independent Component Analysis Local Distortions Operating Mode Perfect Reconstruction Residual Coding Dual-Mode Hierarchical Model High Bitrate Multichannel Audio Signals Reconstructed Speech Spectral Characteristics Complex Variable