ETRI-Knowledge Sharing Plaform

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