{"total":57,"rows":[{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771,"area":null},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687,"area":null},{"id":"2111.09296","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","created":"2021-11-17","cited_by_count":601,"area":null},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588,"area":null},{"id":"2305.13516","title":"Scaling Speech Technology to 1,000+ Languages","created":"2023-05-22","cited_by_count":411,"area":null},{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388,"area":null},{"id":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171,"area":null},{"id":"2105.11084","title":"Unsupervised Speech Recognition","created":"2021-05-24","cited_by_count":148,"area":null},{"id":"2109.11680","title":"Simple and Effective Zero-shot Cross-lingual Phoneme Recognition","created":"2021-09-23","cited_by_count":79,"area":null},{"id":"2310.14228","title":"Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection","created":"2023-10-22","cited_by_count":66,"area":null},{"id":"2107.05677","title":"Codified audio language modeling learns useful representations for music information retrieval","created":"2021-07-12","cited_by_count":64,"area":null},{"id":"2103.01950","title":"Predicting Video with VQVAE","created":"2021-03-02","cited_by_count":61,"area":null},{"id":"2301.12662","title":"SingSong: Generating musical accompaniments from singing","created":"2023-01-30","cited_by_count":55,"area":null},{"id":"2410.14411","title":"SNAC: Multi-Scale Neural Audio Codec","created":"2024-10-18","cited_by_count":43,"area":null},{"id":"2409.17686","title":"MoGenTS: Motion Generation based on Spatial-Temporal Joint Modeling","created":"2024-09-26","cited_by_count":41,"area":null},{"id":"2311.05908","title":"FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores","created":"2023-11-10","cited_by_count":33,"area":null},{"id":"2112.09312","title":"MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling","created":"2021-12-17","cited_by_count":32,"area":null},{"id":"2403.06363","title":"Say Anything with Any Style","created":"2024-03-11","cited_by_count":26,"area":null},{"id":"2103.06089","title":"Variable-rate discrete representation learning","created":"2021-03-10","cited_by_count":24,"area":null},{"id":"2107.09998","title":"Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learning","created":"2021-07-21","cited_by_count":24,"area":null},{"id":"2302.05917","title":"Vector Quantized Wasserstein Auto-Encoder","created":"2023-02-12","cited_by_count":22,"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":"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":"2404.11499","title":"A Data-Driven Representation for Sign Language Production","created":"2024-04-17","cited_by_count":17,"area":null},{"id":"2412.16919","title":"TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction","created":"2024-12-22","cited_by_count":16,"area":null},{"id":"2102.05749","title":"Self-Supervised VQ-VAE for One-Shot Music Style Transfer","created":"2021-02-10","cited_by_count":14,"area":null},{"id":"2110.05999","title":"DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformer","created":"2021-10-12","cited_by_count":14,"area":null},{"id":"2312.10628","title":"T2M-HiFiGPT: Generating High Quality Human Motion from Textual Descriptions with Residual Discrete Representations","created":"2023-12-17","cited_by_count":10,"area":null},{"id":"2506.05104","title":"Survey on the Evaluation of Generative Models in Music","created":"2025-06-05","cited_by_count":10,"area":null},{"id":"2508.04651","title":"Live Music Models","created":"2025-08-06","cited_by_count":10,"area":null},{"id":"2410.15765","title":"SeisLM: a Foundation Model for Seismic Waveforms","created":"2024-10-21","cited_by_count":8,"area":null},{"id":"2502.17726","title":"The GigaMIDI Dataset with Features for Expressive Music Performance Detection","created":"2025-02-24","cited_by_count":7,"area":null},{"id":"2504.03059","title":"Compressing 3D Gaussian Splatting by Noise-Substituted Vector Quantization","created":"2025-04-03","cited_by_count":7,"area":null},{"id":"2208.04554","title":"Hierarchical Residual Learning Based Vector Quantized Variational Autoencoder for Image Reconstruction and Generation","created":"2022-08-09","cited_by_count":6,"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":"2402.08300","title":"An Order-Complexity Aesthetic Assessment Model for Aesthetic-aware Music Recommendation","created":"2024-02-13","cited_by_count":6,"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":"2407.04958","title":"Entropy-Informed Weighting Channel Normalizing Flow for Deep Generative Models","created":"2024-07-06","cited_by_count":5,"area":null},{"id":"2104.00353","title":"CycleDRUMS: Automatic Drum Arrangement For Bass Lines Using CycleGAN","created":"2021-04-01","cited_by_count":4,"area":null},{"id":"2206.14723","title":"DrumGAN VST: A Plugin for Drum Sound Analysis/Synthesis With Autoencoding Generative Adversarial Networks","created":"2022-06-29","cited_by_count":4,"area":null},{"id":"2502.08122","title":"Hookpad Aria: A Copilot for Songwriters","created":"2025-02-12","cited_by_count":4,"area":null},{"id":"2502.12489","title":"A Comprehensive Survey on Generative AI for Video-to-Music Generation","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2105.10371","title":"LoopNet: Musical Loop Synthesis Conditioned On Intuitive Musical Parameters","created":"2021-05-21","cited_by_count":3,"area":null},{"id":"2201.11999","title":"Dual Learning Music Composition and Dance Choreography","created":"2022-01-28","cited_by_count":3,"area":null},{"id":"2306.08230","title":"Unbiased Learning of Deep Generative Models with Structured Discrete Representations","created":"2023-06-14","cited_by_count":2,"area":null},{"id":"2402.15294","title":"A Survey of Music Generation in the Context of Interaction","created":"2024-02-23","cited_by_count":2,"area":null},{"id":"2105.11681","title":"Deep Neural Networks and End-to-End Learning for Audio Compression","created":"2021-05-25","cited_by_count":1,"area":null},{"id":"2108.01043","title":"Musical Speech: A Transformer-based Composition Tool","created":"2021-08-02","cited_by_count":1,"area":null},{"id":"2110.08787","title":"PixelPyramids: Exact Inference Models from Lossless Image Pyramids","created":"2021-10-17","cited_by_count":1,"area":null},{"id":"2201.00052","title":"Evaluating Deep Music Generation Methods Using Data Augmentation","created":"2021-12-31","cited_by_count":1,"area":null},{"id":"2305.15571","title":"Sound Design Strategies for Latent Audio Space Explorations Using Deep Learning Architectures","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2402.01571","title":"Spiking Music: Audio Compression with Event Based Auto-encoders","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2607.00641","title":"What's a Credit Worth? A Market Framework for Attribution-Aware Compensation in Generative Music","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2104.07519","title":"Spectrogram Inpainting for Interactive Generation of Instrument Sounds","created":"2021-04-15","cited_by_count":0,"area":null},{"id":"2209.02388","title":"Pathway to Future Symbiotic Creativity","created":"2022-08-18","cited_by_count":0,"area":null},{"id":"2209.10259","title":"Learning Hierarchical Metrical Structure Beyond Measures","created":"2022-09-21","cited_by_count":0,"area":null},{"id":"2509.22161","title":"Pushing Toward the Simplex Vertices: A Simple Remedy for Code Collapse in Smoothed Vector Quantization","created":"2025-09-26","cited_by_count":0,"area":null}],"next_cursor":null}