{"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/avocodo-generative-adversarial-network-for","title":"Avocodo: Generative Adversarial Network for Artifact-free Vocoder","arxiv_id":"2206.13404","date":"2022-06-27","proceeding":null,"authors":["Taejun Bak","Junmo Lee","Hanbin Bae","Jinhyeok Yang","Jae-Sung Bae","Young-Sun Joo"],"abstract":"Neural vocoders based on the generative adversarial neural network (GAN) have been widely used due to their fast inference speed and lightweight networks while generating high-quality speech waveforms. Since the perceptually important speech components are primarily concentrated in the low-frequency bands, most GAN-based vocoders perform multi-scale analysis that evaluates downsampled speech waveforms. This multi-scale analysis helps the generator improve speech intelligibility. However, in preliminary experiments, we discovered that the multi-scale analysis which focuses on the low-frequency bands causes unintended artifacts, e.g., aliasing and imaging artifacts, which degrade the synthesized speech waveform quality. Therefore, in this paper, we investigate the relationship between these artifacts and GAN-based vocoders and propose a GAN-based vocoder, called Avocodo, that allows the synthesis of high-fidelity speech with reduced artifacts. We introduce two kinds of discriminators to evaluate speech waveforms in various perspectives: a collaborative multi-band discriminator and a sub-band discriminator. We also utilize a pseudo quadrature mirror filter bank to obtain downsampled multi-band speech waveforms while avoiding aliasing. According to experimental results, Avocodo outperforms baseline GAN-based vocoders, both objectively and subjectively, while reproducing speech with fewer artifacts.","url_abs":"https://arxiv.org/abs/2206.13404v3","url_pdf":"https://arxiv.org/pdf/2206.13404v3.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":"avocodo-generative-adversarial-network-for","repo_url":"https://github.com/ncsoft/Avocodo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"avocodo-generative-adversarial-network-for","repo_url":"https://github.com/rishikksh20/Avocodo-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.13404","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}