{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/low-latency-real-time-non-parallel-voice","title":"Low-Latency Real-Time Non-Parallel Voice Conversion based on Cyclic Variational Autoencoder and Multiband WaveRNN with Data-Driven Linear Prediction","arxiv_id":"2105.09858","date":"2021-05-20","proceeding":null,"authors":["Patrick Lumban Tobing","Tomoki Toda"],"abstract":"This paper presents a low-latency real-time (LLRT) non-parallel voice conversion (VC) framework based on cyclic variational autoencoder (CycleVAE) and multiband WaveRNN with data-driven linear prediction (MWDLP). CycleVAE is a robust non-parallel multispeaker spectral model, which utilizes a speaker-independent latent space and a speaker-dependent code to generate reconstructed/converted spectral features given the spectral features of an input speaker. On the other hand, MWDLP is an efficient and a high-quality neural vocoder that can handle multispeaker data and generate speech waveform for LLRT applications with CPU. To accommodate LLRT constraint with CPU, we propose a novel CycleVAE framework that utilizes mel-spectrogram as spectral features and is built with a sparse network architecture. Further, to improve the modeling performance, we also propose a novel fine-tuning procedure that refines the frame-rate CycleVAE network by utilizing the waveform loss from the MWDLP network. The experimental results demonstrate that the proposed framework achieves high-performance VC, while allowing for LLRT usage with a single-core of $2.1$--$2.7$ GHz CPU on a real-time factor of $0.87$--$0.95$, including input/output, feature extraction, on a frame shift of $10$ ms, a window length of $27.5$ ms, and $2$ lookup frames.","url_abs":"https://arxiv.org/abs/2105.09858v2","url_pdf":"https://arxiv.org/pdf/2105.09858v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"low-latency-real-time-non-parallel-voice","repo_url":"https://github.com/patrickltobing/cyclevae-vc-neuralvoco","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"low-latency-real-time-non-parallel-voice","repo_url":"https://github.com/patrickltobing/cyclevae-vc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"voice-conversion","task_name":"Voice Conversion"}],"methods":[{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"wavernn","method_name":"WaveRNN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}