ETRI-Knowledge Sharing Plaform

Deep Neural Network(DNN) Audio Codec Interactive Music Network-Based Mpeg Surround Music Application High Performance Speech Coding Proposed Model Audio Features Subjective Listening Tests Side Information Sound Quality Post-Processing Video Service Perceptual Quality Speech Synthesis System Low Bit Rate Speech Codec Non-Speech Emotional Speech Generative Models Conventional Methods Superior Performance Analysis And Synthesis Sound Source Full-Band File Format Spatial Cue Synthesized Speech Learning-Based Deep Learning(DL) Stereo Audio Audio Description Music Industry Multichannel Audio High-Quality Statistical Parametric Speech Synthesis(SPSS) Modified Discrete Cosine Transform(MDCT) Acoustic Parameters Additional Information Coding Gain Latent Space Audio Analysis Subjective Evaluation Convolutive Source Separation Text-To-Speech Synthesis Head-Related Transfer Function Digital Music Basic Media Speech Signals Generative Adversarial Network Psychoacoustic Model Bit Allocation Audio Synthesis Temporal Structure Coding Models Parameter Selection Noise Reduction(NR) Spectral Parameters Separation Techniques Adaptive Quantization Media Content Perceptual Weighting Real-World Applications Range Of Target Tactile Devices Spatial Image Subjective Test Time-Domain Computational Load Fine-Tuning Adversarial Training Data Compression Objective Assessment Visualization Tool Source Location Virtual Source Audio Feature Extraction High-Pass Filtering Low Resource Speech Communication Text-To-Speech System Waveform Reconstruction Compression Efficiency Frequency Band Sub-Band Signal Reconstruction Coding System Fundamental Frequency(F0) Independent Component Analysis Speech Enhancement Different Dimensions Filtering Method Analysis-By-Synthesis Flow Factor Excitation Signals Weight Control Computational Resources Optimal Transformation Open Source Signal Generation Computational Cost Control Algorithm Numerical Experiments Perceptual Speech Quality Sub-Nyquist Sampling Audio Recording Audio Data Frequency Domain Adaptive Filter Reconstruction Performance Speaker Recognition Enhancement Scheme Flexible Features Frame Rate(FR) Nyquist Rate Signal Characteristics Speech Characteristics Bandwidth Extension Mobile Station(MS) Sinusoidal Vibration Vibration Signal Source-Filter Model As 4 Relative Gradient Quantization Noise Nonlinear Function Selection Strategy Coding Scheme Independent Control Low-Rate Novel Method Quality Estimation Reconstruction Quality Transform Coding Speech Separation Acoustic Echo Cancellation Dynamic Characteristics Joint Diagonalization High-Band State-Of-The-Art Entropy Model Prediction And Analysis Residual Error Vocal Tract Spectral Bandwidth Time-Frequency Resolution Interpolation Technique Sensor Noise Subjective Quality Training Criteria Backward Compatibility Emotion Classification Location Information Synchronous Approach Continuous Space Objective Evaluation Compact Representation Spatial Audio Coding Signal Processing Techniques High Efficiency Synthesis Method Data-Driven Low Pass Filter(LPF) Network Architecture Post-Processor Simulation Results Speech Detection Time-Frequency Characteristics High-Dimensional Transfer Function Model Audio Signal Compression Weighted Sum Backward Compatible Noisy Data Partitioned Block Frequency Domain Selection Problem Audio Compression Design Scheme Error Rate Diffusion Model Data Augmentation Glottal Closure Instants Narrow Bandwidth Convolutive Mixtures Memory Usage Neutral Speech Vector Space Emotion Control Power Spectra Convolution Neural Network(CNN) Automatic Music Transcription(AMT) Multichannel Signals Permutation Ambiguity Semi-Automatic Variable Step-Size(VSS) Blind Deconvolution Moving Picture Experts Group(MPEG) Representation Learning Discrimination Method Hearing Impaired People Linear Prediction Analysis Model Complexity Separation Performance Blind Separation Source Characteristics Siamese Network Speaker Embeddings Scalar Quantization Blind Source Separation(BSS) Multi-Stage Vector Quantization Feature Extraction Method Second Order Statistics(SOS) Audio Information Musical Rhythm Information Reconstruction Stereo Coding Audio Quality Discrete-Time Feature Transformation Objective Test Stereo Sound Training Samples End-To-End Learning Skip Connections Acoustic Characteristics Effective Frequency Frequency-Domain Method Low-Dimensional Subjective Assessment Speech Discrimination Pitch Information User Interactivity Waveform Synthesis Control Method Gradient Method Music Player Optimization Techniques Audio Signal Processing Based Approach Distortion Ratio Pitch-Synchronous Enhanced Structure Estimation Model Level Difference Computational Efficiency Perceptual Evaluation Of Speech Quality Side Effects Perceptual Similarity De-Quantization Frequency Dependent Model Compression Training Data Telepresence System Classification Accuracy Speech Features Warped Linear Prediction Weight-Based Coupling Effects Cbs Algorithm Speech Analysis Various Approaches Convergence Speed End-To-End Training Emotional Expression Fixed Dimension Implementation Scheme Coding Algorithm Control Technique Root-Mean-Square(RMS) Multi-Band Separation Algorithm