ETRI-Knowledge Sharing Plaform

Deep Neural Network(DNN) Loss Function Speech Codec End To End(E2E) Perceptual Quality Speech Coder Subjective Test ITU-T AMR-WB Speech Signals Speech Compression Wide Range Transmission Gate(TG) Residual Learning Model Complexity Psychoacoustic Model Linear Predictive Coding(LPC) State-Of-The-Art Cross-Module Scale Up Speech Coding Low Bit Rate Compression Problem Domain Specific Entropy Coding High Bitrate Modified Discrete Cosine Transform(MDCT) Model Components Complex Architecture Convolution Neural Network(CNN) Two-Stage Two-Phase 3d Audio Encoding And Decoding Unified Speech And Audio Coding(USAC) Next-Generation Spatial Audio Training Method Frequency Domain(FD) Model-Based Coding Non-Parametric Network Architecture Switching System Stereo Audio Scalable Architecture Basic Media Decoding Complexity Quality Level Voice Codecs Entropy-Based Linear Prediction Mode Of Operation Spectral Coefficients Super Wideband(SWB) Sound Quality Scale Down Computational Capacity Coding System Coding Artifacts Digital Signal Processing Methods Weighting Scheme Live Concert Multi Time Scale Mel-Frequency Single Mode Stochastic Noise Superior Performance Compact Model High Reality Filter Model Generation Technology Hybrid Design Multi-Resolution Residual Network Transform Coding Training Scheme Uniform Quantization Subjective Quality Generative Models Large Numbers Neural Network Model Optimization Process Coding Algorithm Compression Performance Compact Representation Data Transmission Transition Control Temporal Noise Shaping Frequency Band Mpeg Surround MPEG-H Quantization Noise Residual Coding Speaker Verification