{"ID":2892786,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.14534","arxiv_id":"2507.14534","title":"Conan: A Chunkwise Online Network for Zero-Shot Adaptive Voice Conversion","abstract":"Zero-shot online voice conversion (VC) holds significant promise for real-time communications and entertainment. However, current VC models struggle to preserve semantic fidelity under real-time constraints, deliver natural-sounding conversions, and adapt effectively to unseen speaker characteristics. To address these challenges, we introduce Conan, a chunkwise online zero-shot voice conversion model that preserves the content of the source while matching the voice timbre and styles of reference speech. Conan comprises three core components: 1) a Stream Content Extractor that leverages Emformer for low-latency streaming content encoding; 2) an Adaptive Style Encoder that extracts fine-grained stylistic features from reference speech for enhanced style adaptation; 3) a Causal Shuffle Vocoder that implements a fully causal HiFiGAN using a pixel-shuffle mechanism. Experimental evaluations demonstrate that Conan outperforms baseline models in subjective and objective metrics. Audio samples can be found at https://aaronz345.github.io/ConanDemo.","short_abstract":"Zero-shot online voice conversion (VC) holds significant promise for real-time communications and entertainment. However, current VC models struggle to preserve semantic fidelity under real-time constraints, deliver natural-sounding conversions, and adapt effectively to unseen speaker characteristics. To address these...","url_abs":"https://arxiv.org/abs/2507.14534","url_pdf":"https://arxiv.org/pdf/2507.14534v4","authors":"[\"Yu Zhang\",\"Baotong Tian\",\"Zhiyao Duan\"]","published":"2025-07-19T08:32:07Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.CL\",\"cs.SD\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}