{"ID":2856488,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.11646","arxiv_id":"2510.11646","title":"BridgeCode: A Dual Speech Representation Paradigm for Autoregressive Zero-Shot Text-to-Speech Synthesis","abstract":"Autoregressive (AR) frameworks have recently achieved remarkable progress in zero-shot text-to-speech (TTS) by leveraging discrete speech tokens and large language model techniques. Despite their success, existing AR-based zero-shot TTS systems face two critical limitations: (i) an inherent speed-quality trade-off, as sequential token generation either reduces frame rates at the cost of expressiveness or enriches tokens at the cost of efficiency, and (ii) a text-oriented supervision mismatch, as cross-entropy loss penalizes token errors uniformly without considering the fine-grained acoustic similarity among adjacent tokens. To address these challenges, we propose BridgeTTS, a novel AR-TTS framework built upon the dual speech representation paradigm BridgeCode. BridgeTTS reduces AR iterations by predicting sparse tokens while reconstructing rich continuous features for high-quality synthesis. Joint optimization of token-level and feature-level objectives further enhances naturalness and intelligibility. Experiments demonstrate that BridgeTTS achieves competitive quality and speaker similarity while significantly accelerating synthesis. Speech demos are available at https://test1562.github.io/demo/.","short_abstract":"Autoregressive (AR) frameworks have recently achieved remarkable progress in zero-shot text-to-speech (TTS) by leveraging discrete speech tokens and large language model techniques. Despite their success, existing AR-based zero-shot TTS systems face two critical limitations: (i) an inherent speed-quality trade-off, as...","url_abs":"https://arxiv.org/abs/2510.11646","url_pdf":"https://arxiv.org/pdf/2510.11646v1","authors":"[\"Jingyuan Xing\",\"Mingru Yang\",\"Zhipeng Li\",\"Xiaofen Xing\",\"Xiangmin Xu\"]","published":"2025-10-13T17:27:05Z","proceeding":"cs.SD","tasks":"[\"cs.SD\"]","methods":"[\"Language Model\"]","has_code":false}