ETRI-Knowledge Sharing Plaform

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