{"total":18,"rows":[{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340,"area":null},{"id":"2104.00355","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","created":"2021-04-01","cited_by_count":243,"area":null},{"id":"2109.03264","title":"Text-Free Prosody-Aware Generative Spoken Language Modeling","created":"2021-09-07","cited_by_count":119,"area":null},{"id":"2107.10394","title":"StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion","created":"2021-07-21","cited_by_count":58,"area":null},{"id":"2111.07402","title":"Textless Speech Emotion Conversion using Discrete and Decomposed Representations","created":"2021-11-14","cited_by_count":29,"area":null},{"id":"2306.14422","title":"The Singing Voice Conversion Challenge 2023","created":"2023-06-26","cited_by_count":25,"area":null},{"id":"2109.06912","title":"fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit","created":"2021-09-14","cited_by_count":24,"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":"2309.02232","title":"FSD: An Initial Chinese Dataset for Fake Song Detection","created":"2023-09-05","cited_by_count":12,"area":null},{"id":"2101.06842","title":"Hierarchical disentangled representation learning for singing voice conversion","created":"2021-01-18","cited_by_count":9,"area":null},{"id":"2110.04754","title":"Towards High-fidelity Singing Voice Conversion with Acoustic Reference and Contrastive Predictive Coding","created":"2021-10-10","cited_by_count":8,"area":null},{"id":"2210.11096","title":"Robust One-Shot Singing Voice Conversion","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2407.07728","title":"SaMoye: Zero-shot Singing Voice Conversion Model Based on Feature Disentanglement and Enhancement","created":"2024-07-10","cited_by_count":5,"area":null},{"id":"2111.09146","title":"Rapping-Singing Voice Synthesis based on Phoneme-level Prosody Control","created":"2021-11-17","cited_by_count":2,"area":null},{"id":"2305.15055","title":"Iteratively Improving Speech Recognition and Voice Conversion","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2310.05203","title":"A Comparative Study of Voice Conversion Models with Large-Scale Speech and Singing Data: The T13 Systems for the Singing Voice Conversion Challenge 2023","created":"2023-10-08","cited_by_count":2,"area":null},{"id":"2302.13678","title":"A Comparative Analysis Of Latent Regressor Losses For Singing Voice Conversion","created":"2023-02-27","cited_by_count":1,"area":null},{"id":"2409.14131","title":"Are Music Foundation Models Better at Singing Voice Deepfake Detection? Far-Better Fuse them with Speech Foundation Models","created":"2024-09-21","cited_by_count":0,"area":null}],"next_cursor":null}