{"total":18,"rows":[{"id":"2304.08490","title":"Conditional Generation of Audio from Video via Foley Analogies","created":"2023-04-17","cited_by_count":52,"area":null},{"id":"2105.00335","title":"Audio Transformers","created":"2021-05-01","cited_by_count":41,"area":null},{"id":"2106.16036","title":"A Generative Model for Raw Audio Using Transformer Architectures","created":"2021-06-30","cited_by_count":18,"area":null},{"id":"2409.14340","title":"Self-Supervised Audio-Visual Soundscape Stylization","created":"2024-09-22","cited_by_count":8,"area":null},{"id":"2205.01800","title":"Synthesized Speech Detection Using Convolutional Transformer-Based Spectrogram Analysis","created":"2022-05-03","cited_by_count":5,"area":null},{"id":"2502.16914","title":"ENACT-Heart -- ENsemble-based Assessment Using CNN and Transformer on Heart Sounds","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2603.15597","title":"AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2108.06128","title":"Pruning vs XNOR-Net: A Comprehensive Study of Deep Learning for Audio Classification on Edge-devices","created":"2021-08-13","cited_by_count":3,"area":null},{"id":"2205.01806","title":"Frequency Domain-Based Detection of Generated Audio","created":"2022-05-03","cited_by_count":3,"area":null},{"id":"2110.03183","title":"Attention is All You Need? Good Embeddings with Statistics are enough:Large Scale Audio Understanding without Transformers/ Convolutions/ BERTs/ Mixers/ Attention/ RNNs or ....","created":"2021-10-07","cited_by_count":1,"area":null},{"id":"2506.19014","title":"IndieFake Dataset: A Benchmark Dataset for Audio Deepfake Detection","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2110.02411","title":"Voice Aging with Audio-Visual Style Transfer","created":"2021-10-05","cited_by_count":0,"area":null},{"id":"2110.12855","title":"Actions Speak Louder than Listening: Evaluating Music Style Transfer based on Editing Experience","created":"2021-10-25","cited_by_count":0,"area":null},{"id":"2210.15750","title":"One-Shot Acoustic Matching Of Audio Signals -- Learning to Hear Music In Any Room/ Concert Hall","created":"2022-10-27","cited_by_count":0,"area":null},{"id":"2212.02886","title":"GAS-NeXt: Few-Shot Cross-Lingual Font Generator","created":"2022-12-06","cited_by_count":0,"area":null},{"id":"2303.10446","title":"Content Adaptive Front End For Audio Classification","created":"2023-03-18","cited_by_count":0,"area":null},{"id":"2308.10388","title":"Neural Architectures Learning Fourier Transforms, Signal Processing and Much More....","created":"2023-08-20","cited_by_count":0,"area":null},{"id":"2602.16721","title":"Speech to Speech Synthesis for Voice Impersonation","created":"2026-02-13","cited_by_count":0,"area":null}],"next_cursor":null}