{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"2110.05069","title":"Efficient Training of Audio Transformers with Patchout","created":"2021-10-11","cited_by_count":226},{"id":"1704.01279","title":"Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders","created":"2017-04-05","cited_by_count":225},{"id":"1812.08466","title":"Fr\\'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms","created":"2018-12-20","cited_by_count":225},{"id":"2211.08553","title":"Hybrid Transformers for Music Source Separation","created":"2022-11-15","cited_by_count":134},{"id":"1710.11153","title":"Onsets and Frames: Dual-Objective Piano Transcription","created":"2017-10-30","cited_by_count":94},{"id":"2103.09410","title":"Contrastive Learning of Musical Representations","created":"2021-03-17","cited_by_count":82},{"id":"2111.03017","title":"MT3: Multi-Task Multitrack Music Transcription","created":"2021-11-04","cited_by_count":71},{"id":"2205.07547","title":"SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization","created":"2022-05-16","cited_by_count":68},{"id":"2107.05677","title":"Codified audio language modeling learns useful representations for music information retrieval","created":"2021-07-12","cited_by_count":64},{"id":"1612.08727","title":"Creating A Multi-track Classical Musical Performance Dataset for Multimodal Music Analysis: Challenges, Insights, and Applications","created":"2016-12-27","cited_by_count":61},{"id":"2010.01815","title":"High-resolution Piano Transcription with Pedals by Regressing Onset and Offset Times","created":"2020-10-05","cited_by_count":61},{"id":"1611.09827","title":"Learning Features of Music from Scratch","created":"2016-11-29","cited_by_count":58},{"id":"2204.12260","title":"Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representation","created":"2022-04-26","cited_by_count":52},{"id":"2111.12124","title":"Towards Learning Universal Audio Representations","created":"2021-11-23","cited_by_count":51},{"id":"1909.06654","title":"musicnn: Pre-trained convolutional neural networks for music audio tagging","created":"2019-09-14","cited_by_count":50},{"id":"2305.15719","title":"Efficient Neural Music Generation","created":"2023-05-25","cited_by_count":50},{"id":"2108.13559","title":"Music Demixing Challenge 2021","created":"2021-08-31","cited_by_count":38},{"id":"2306.10548","title":"MARBLE: Music Audio Representation Benchmark for Universal Evaluation","created":"2023-06-18","cited_by_count":38},{"id":"2309.02612","title":"Music Source Separation with Band-Split RoPE Transformer","created":"2023-09-05","cited_by_count":37},{"id":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37},{"id":"2203.07960","title":"Investigating self-supervised learning for speech enhancement and separation","created":"2022-03-15","cited_by_count":35},{"id":"2210.03799","title":"Supervised and Unsupervised Learning of Audio Representations for Music Understanding","created":"2022-10-07","cited_by_count":35},{"id":"1907.01277","title":"Conditioned-U-Net: Introducing a Control Mechanism in the U-Net for Multiple Source Separations","created":"2019-07-02","cited_by_count":27},{"id":"2010.10291","title":"Automatic multitrack mixing with a differentiable mixing console of neural audio effects","created":"2020-10-20","cited_by_count":27},{"id":"2401.00365","title":"HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes","created":"2023-12-31","cited_by_count":27},{"id":"2204.03339","title":"Boosting Self-Supervised Embeddings for Speech Enhancement","created":"2022-04-07","cited_by_count":24},{"id":"2212.01884","title":"Melody transcription via generative pre-training","created":"2022-12-04","cited_by_count":24},{"id":"2307.04305","title":"Automatic Piano Transcription with Hierarchical Frequency-Time Transformer","created":"2023-07-10","cited_by_count":22},{"id":"2107.04954","title":"ReconVAT: A Semi-Supervised Automatic Music Transcription Framework for Low-Resource Real-World Data","created":"2021-07-11","cited_by_count":20},{"id":"2308.06979","title":"The Sound Demixing Challenge 2023 $\\unicode{x2013}$ Music Demixing Track","created":"2023-08-14","cited_by_count":20},{"id":"2211.02247","title":"Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effects","created":"2022-11-04","cited_by_count":18},{"id":"1906.09165","title":"Deep Polyphonic ADSR Piano Note Transcription","created":"2019-06-21","cited_by_count":15},{"id":"2406.17672","title":"SpecMaskGIT: Masked Generative Modeling of Audio Spectrograms for Efficient Audio Synthesis and Beyond","created":"2024-06-25","cited_by_count":15},{"id":"1907.04294","title":"An Attention Mechanism for Musical Instrument Recognition","created":"2019-07-09","cited_by_count":14},{"id":"1706.02921","title":"End-to-End Musical Key Estimation Using a Convolutional Neural Network","created":"2017-06-09","cited_by_count":13},{"id":"1906.08512","title":"Adversarial Learning for Improved Onsets and Frames Music Transcription","created":"2019-06-20","cited_by_count":13},{"id":"2208.11428","title":"Automatic music mixing with deep learning and out-of-domain data","created":"2022-08-24","cited_by_count":11},{"id":"2104.06607","title":"Revisiting the Onsets and Frames Model with Additive Attention","created":"2021-04-14","cited_by_count":9},{"id":"2206.12230","title":"Deformable CNN and Imbalance-Aware Feature Learning for Singing Technique Classification","created":"2022-06-24","cited_by_count":8},{"id":"2302.08136","title":"An Attention-based Approach to Hierarchical Multi-label Music Instrument Classification","created":"2023-02-16","cited_by_count":7},{"id":"2407.08889","title":"Diff-MST: Differentiable Mixing Style Transfer","created":"2024-07-11","cited_by_count":6},{"id":"2304.03407","title":"Adoption of AI Technology in the Music Mixing Workflow: An Investigation","created":"2023-04-06","cited_by_count":4}],"next_cursor":null}