{"total":17,"rows":[{"id":"2111.03017","title":"MT3: Multi-Task Multitrack Music Transcription","created":"2021-11-04","cited_by_count":71,"area":null},{"id":"2307.05527","title":"The Ethical Implications of Generative Audio Models: A Systematic Literature Review","created":"2023-07-07","cited_by_count":18,"area":null},{"id":"2406.00146","title":"A Survey of Deep Learning Audio Generation Methods","created":"2024-05-31","cited_by_count":5,"area":null},{"id":"2409.11836","title":"NT-ViT: Neural Transcoding Vision Transformers for EEG-to-fMRI Synthesis","created":"2024-09-18","cited_by_count":4,"area":null},{"id":"2209.00291","title":"Generating Coherent Drum Accompaniment With Fills And Improvisations","created":"2022-09-01","cited_by_count":2,"area":null},{"id":"2412.11449","title":"Whisper-GPT -- Continuous Discrete Hybrid Representation Language Models For Speech And Music","created":"2024-12-16","cited_by_count":2,"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":"2307.00461","title":"Conformer LLMs -- Convolution Augmented Large Language Models","created":"2023-07-02","cited_by_count":1,"area":null},{"id":"2409.10870","title":"Adaptive Large Language Models By Layerwise Attention Shortcuts","created":"2024-09-17","cited_by_count":1,"area":null},{"id":"2409.12924","title":"Wavelet GPT: Wavelet Inspired Large Language Models","created":"2024-09-04","cited_by_count":1,"area":null},{"id":"2505.17091","title":"Large Language Models Implicitly Learn to See and Hear Just By Reading","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2208.07994","title":"Enhancing Audio Perception of Music By AI Picked Room Acoustics","created":"2022-08-16","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":"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":"2308.12408","title":"An Initial Exploration: Learning to Generate Realistic Audio for Silent Video","created":"2023-08-23","cited_by_count":0,"area":null},{"id":"2402.15923","title":"Predicting Outcomes in Video Games with Long Short Term Memory Networks","created":"2024-02-24","cited_by_count":0,"area":null}],"next_cursor":null}