{"total":20,"rows":[{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184,"area":null},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2102.01106","title":"Universal Neural Vocoding with Parallel WaveNet","created":"2021-02-01","cited_by_count":25,"area":null},{"id":"2202.07968","title":"On loss functions and evaluation metrics for music source separation","created":"2022-02-16","cited_by_count":17,"area":null},{"id":"2106.06426","title":"Catch-A-Waveform: Learning to Generate Audio from a Single Short Example","created":"2021-06-11","cited_by_count":15,"area":null},{"id":"2201.02490","title":"Audio representations for deep learning in sound synthesis: A review","created":"2022-01-07","cited_by_count":9,"area":null},{"id":"2405.18213","title":"NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields","created":"2024-05-28","cited_by_count":9,"area":null},{"id":"2312.14507","title":"Unsupervised Harmonic Parameter Estimation Using Differentiable DSP and Spectral Optimal Transport","created":"2023-12-22","cited_by_count":8,"area":null},{"id":"2301.06468","title":"Msanii: High Fidelity Music Synthesis on a Shoestring Budget","created":"2023-01-16","cited_by_count":6,"area":null},{"id":"2407.16643","title":"Synthesizer Sound Matching Using Audio Spectrogram Transformers","created":"2024-07-23","cited_by_count":4,"area":null},{"id":"2306.08956","title":"Multi-Loss Convolutional Network with Time-Frequency Attention for Speech Enhancement","created":"2023-06-15","cited_by_count":2,"area":null},{"id":"2312.06118","title":"ROSE: A Recognition-Oriented Speech Enhancement Framework in Air Traffic Control Using Multi-Objective Learning","created":"2023-12-11","cited_by_count":2,"area":null},{"id":"2202.02310","title":"EcoFlow: Efficient Convolutional Dataflows for Low-Power Neural Network Accelerators","created":"2022-02-04","cited_by_count":1,"area":null},{"id":"2409.06513","title":"Sines, Transient, Noise Neural Modeling of Piano Notes","created":"2024-09-10","cited_by_count":1,"area":null},{"id":"2505.04457","title":"Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2505.13268","title":"Representation of perceived prosodic similarity of conversational feedback","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2406.11006","title":"SPEAR: Receiver-to-Receiver Acoustic Neural Warping Field","created":"2024-06-16","cited_by_count":0,"area":null},{"id":"2502.17477","title":"Frequency-Aware Masked Autoencoders for Human Activity Recognition using Accelerometers","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2505.24498","title":"Efficient Neural and Numerical Methods for High-Quality Online Speech Spectrogram Inversion via Gradient Theorem","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2609.25948","title":"Challenges of Multi-Speaker Extraction for Real Conversational Speech Enhancement","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":null}