ETRI-Knowledge Sharing Plaform

Audio Coding Mpeg Surround Deep Neural Network(DNN) Sound Source Interactive Music Audio Signal Audio Codec Emotional Speech Network-Based Post-Processing Music Application Audio Features Synthesized Speech File Format Learning-Based Spatial Cue Non-Speech Acoustic Parameters Side Information Statistical Parametric Speech Synthesis(SPSS) Multichannel Audio Speech Codec Audio Synthesis Music Industry Deep Learning(DL) Subjective Listening Tests Speech Synthesis System Speech Coding Low Bit Rate Audio Analysis Source Location Level Difference Acoustic Echo Cancellation Audio Feature Extraction Dynamic Characteristics Filtering Method Flexible Features Lowpass Filter Moving Picture Experts Group(MPEG) Low-Resource Media Content Novel Method Partitioned Block Frequency Domain Prediction And Analysis Parameter Selection Speech Detection Virtual Source Audio Information Spectral Parameters High Performance High-Quality Weighted Sum Location Information(GPS) Coupling Effects Digital Music Frame Rate Low-Rate Power Spectra Text-To-Speech System Time-Frequency Resolution Text-To-Speech Synthesis High-Pass Filtering Blind Source Separation(BSS) Backward Compatibility De-Quantization Emotional Expression Emotion Classification Selection Strategy Source-Filter Model Network Architecture Pitch-Synchronous Speech Features Semi-Automatic Stereo Audio Training Data Video Service Glottal Closure Instants Generative Adversarial Network Warped Linear Prediction Automatic Music Transcription(AMT) Basic Media Control Method Excitation Signal Frequency Dependent Speech Enhancement Latent Space Sound Quality Pitch Information Synchronous Approach Signal Generation Various Approaches Vector Space Linear Prediction Analysis As 4 Speech Communication Temporal Structure High Efficiency Waveform Reconstruction Acoustic Characteristics Convolutive Source Separation Coding System Conventional Methods Classification Accuracy Design Scheme Discrete-Time Feature Extraction Method Fixed Dimension Permutation Ambiguity Multi-Band Neutral Speech Numerical Experiments Post-Processor Residual Error Speech Analysis Synthesis Method Superior Performance Separation Techniques Vocal Tract Visualization Tool Selection Problem Head-Related Transfer Function Implementation Scheme Weight Control Weight-Based Additional Information Audio Recording Analysis And Synthesis Emotion Control Spatial Image Perceptual Quality Sub-Nyquist Sampling Speech Separation Telepresence System Transfer Function Model Hearing Impaired People Audio Description Control Technique Data Augmentation Frequency-Domain Method Enhancement Scheme End-To-End Training Frequency Domain Adaptive Filter Musical Rhythm Multi-Stage Vector Quantization Subjective Assessment Nyquist Rate Narrow Bandwidth Subjective Test Subjective Quality Tactile Device User Interactivity Time-Frequency Characteristics Full-Band Interpolation Technique Independent Component Analysis Analysis-By-Synthesis Blind Separation Compact Representation Coding Algorithm Fundamental Frequency Music Player Noisy Data Speaker Recognition Second-Order Simulation Results Subjective Evaluation Training Samples Variable Step Size Sensor Noise