{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T08:05:18Z","timestamp":1784534718272,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234257","type":"print"},{"value":"9789819234264","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T00:00:00Z","timestamp":1784592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T00:00:00Z","timestamp":1784592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-981-92-3426-4_45","type":"book-chapter","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T07:31:02Z","timestamp":1784532662000},"page":"538-549","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ASTE: Accent-Sensitive Token Editing for Accent Correction in Neural Codec Speech"],"prefix":"10.1007","author":[{"given":"Yibin","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,21]]},"reference":[{"key":"45_CR1","unstructured":"Du, Z., Gao, C., Wang, Y., et al.: CosyVoice 3: Towards in-the-wild speech generation via scaling-up and post-training. arXiv preprint https:\/\/arxiv.org\/abs\/2505.17589 (2025)"},{"key":"45_CR2","first-page":"11341","volume-title":"2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"S Mehta","year":"2024","unstructured":"Mehta, S., Tu, R., Beskow, J., et al.: Matcha-TTS: a fast TTS architecture with conditional flow matching. In: 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 11341\u201311345 (2024)"},{"key":"45_CR3","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1109\/TASLPRO.2025.3530270","volume":"33","author":"S Chen","year":"2025","unstructured":"Chen, S., Wang, C., Wu, Y., et al.: Neural codec language models are zero-shot text-to-speech synthesizers. IEEE\/ACM Trans. Audio Speech Lang. Process. 33, 705\u2013718 (2025)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"45_CR4","first-page":"1","volume-title":"2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"X Lyu","year":"2025","unstructured":"Lyu, X., Wang, Y., Zhao, T., et al.: Build LLM-based zero-shot streaming TTS system with CosyVoice. In: 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20132 (2025)"},{"key":"45_CR5","unstructured":"Du, Z., Wang, Y., Chen, Q., et al.: CosyVoice 2: Scalable streaming speech synthesis with large language models. arXiv preprint https:\/\/arxiv.org\/abs\/2412.10117 (2024)"},{"key":"45_CR6","unstructured":"Du, Z., Chen, Q., Zhang, S., et al.: CosyVoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens. arXiv preprint https:\/\/arxiv.org\/abs\/2407.05407 (2024)"},{"key":"45_CR7","first-page":"5210","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML)","author":"K Qian","year":"2019","unstructured":"Qian, K., Zhang, Y., Chang, S., et al.: AutoVC: zero-shot voice style transfer with only autoencoder loss. In: Proceedings of the 36th International Conference on Machine Learning (ICML), pp. 5210\u20135219 (2019)"},{"key":"45_CR8","unstructured":"Yang, D., Liu, S., Huang, R., et al.: InstructTTS: Modelling expressive TTS in discrete latent space with natural language style prompt. arXiv preprint https:\/\/arxiv.org\/abs\/2301.13662 (2023)"},{"key":"45_CR9","doi-asserted-by":"crossref","unstructured":"Nguyen, T.N., Pham, N.Q., Waibel, A.: Accent conversion using discrete units with parallel data synthesized from controllable accented TTS. arXiv preprint https:\/\/arxiv.org\/abs\/2410.03734 (2024)","DOI":"10.21437\/SynData4GenAI.2024-11"},{"key":"45_CR10","unstructured":"D\u00e9fossez, A., Copet, J., Synnaeve, G., et al.: High fidelity neural audio compression. arXiv preprint https:\/\/arxiv.org\/abs\/2210.13438 (2022)"},{"key":"45_CR11","unstructured":"Andreev, P., Alanov, A., Ivanov, O., et al.: HiFi++: A unified framework for neural vocoding, bandwidth extension and speech enhancement. arXiv preprint https:\/\/arxiv.org\/abs\/2203.13086 (2022)"},{"key":"45_CR12","doi-asserted-by":"publisher","first-page":"1344","DOI":"10.21437\/Interspeech.2021-283","volume-title":"Proceedings of the Interspeech 2021","author":"D Wang","year":"2021","unstructured":"Wang, D., Deng, L., Yeung, Y.T., et al.: VQMIVC: vector quantization and mutual information-based unsupervised speech representation disentanglement for one-shot voice conversion. In: Proceedings of the Interspeech 2021, pp. 1344\u20131348 (2021)"},{"key":"45_CR13","unstructured":"Yang, D., Liu, S., Huang, R., et al.: HiFi-Codec: Group-residual vector quantization for high fidelity audio codec. arXiv preprint https:\/\/arxiv.org\/abs\/2305.02765 (2023)"},{"key":"45_CR14","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1109\/TASLP.2021.3129994","volume":"30","author":"N Zeghidour","year":"2022","unstructured":"Zeghidour, N., Luebs, A., Omran, A., et al.: SoundStream: an end-to-end neural audio codec. IEEE\/ACM Trans. Audio Speech Lang. Process. 30, 495\u2013507 (2022)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"45_CR15","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"W Hsu","year":"2021","unstructured":"Hsu, W., Bolte, B., Tsai, Y.H., et al.: HuBERT: self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 3451\u20133460 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"45_CR16","unstructured":"Borsos, Z., Marinier, R., Vincent, D., et al.: AudioLM: A language modeling approach to audio generation. arXiv preprint https:\/\/arxiv.org\/abs\/2209.03143 (2022)"},{"key":"45_CR17","unstructured":"Du, Z., Zhang, S., Hu, K., et al.: FunCodec: A fundamental, reproducible and integrable open-source toolkit for neural speech codec. arXiv preprint https:\/\/arxiv.org\/abs\/2309.07405 (2023)"},{"key":"45_CR18","unstructured":"Zhang, C., Zhang, C., Zheng, S., et al.: A survey on audio diffusion models: Text to speech synthesis and enhancement in generative AI. arXiv preprint https:\/\/arxiv.org\/abs\/2303.13336 (2023)"},{"key":"45_CR19","doi-asserted-by":"publisher","first-page":"11655","DOI":"10.18653\/v1\/2023.findings-acl.741","volume-title":"Findings of the Association for Computational Linguistics: ACL 2023","author":"Z Jiang","year":"2023","unstructured":"Jiang, Z., Yang, Q., Zuo, J., et al.: FluentSpeech: stutter-oriented automatic speech editing with context-aware diffusion models. In: Findings of the Association for Computational Linguistics: ACL 2023, pp. 11655\u201311671 (2023)"},{"key":"45_CR20","unstructured":"Chen, J., Jia, Y., Wang, H., et al.: CosyEdit: Unlocking end-to-end speech editing capability from zero-shot text-to-speech models. arXiv preprint https:\/\/arxiv.org\/abs\/2601.05329 (2026)"},{"key":"45_CR21","doi-asserted-by":"crossref","unstructured":"Tan, D., Deng, L., Yeung, Y.T., et al.: EditSpeech: A text based speech editing system using partial inference and bidirectional fusion. arXiv preprint https:\/\/arxiv.org\/abs\/2107.01554 (2021)","DOI":"10.1109\/ASRU51503.2021.9688051"},{"key":"45_CR22","unstructured":"Qin, Z., Zhao, W., Yu, X., et al.: OpenVoice: Versatile instant voice cloning. arXiv preprint https:\/\/arxiv.org\/abs\/2312.01479 (2024)"},{"key":"45_CR23","unstructured":"Chen, Q., Chen, Y., Chen, Y., et al.: Minmo: A multimodal large language model for seamless voice interaction. arXiv preprint https:\/\/arxiv.org\/abs\/2501.06282 (2025)"},{"key":"45_CR24","doi-asserted-by":"publisher","first-page":"1593","DOI":"10.21437\/Interspeech.2023-1428","volume-title":"Proceedings of the Interspeech 2023","author":"Z Gao","year":"2023","unstructured":"Gao, Z., Li, Z., Wang, J., et al.: FunASR: a fundamental end-to-end speech recognition toolkit. In: Proceedings of the Interspeech 2023, pp. 1593\u20131597 (2023)"},{"key":"45_CR25","doi-asserted-by":"crossref","unstructured":"Chen, Y., Niu, Z., Ma, Z., et al.: F5-TTS: A fairytaler that fakes fluent and faithful speech with flow matching. arXiv preprint https:\/\/arxiv.org\/abs\/2410.06885 (2024)","DOI":"10.18653\/v1\/2025.acl-long.313"},{"key":"45_CR26","first-page":"17022","volume":"33","author":"J Kong","year":"2020","unstructured":"Kong, J., Kim, J., Bae, J.: HiFi-GAN: generative adversarial networks for efficient and high fidelity speech synthesis. Adv. Neural Inf. Proces. Syst. 33, 17022\u201317033 (2020)","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"45_CR27","doi-asserted-by":"publisher","first-page":"2783","DOI":"10.21437\/Interspeech.2018-1110","volume-title":"Proceedings of the Interspeech 2018","author":"G Zhao","year":"2018","unstructured":"Zhao, G., Sonsaat, S., Silpachai, A., et al.: L2-ARCTIC: a non-native English speech corpus. In: Proceedings of the Interspeech 2018, pp. 2783\u20132787 (2018)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3426-4_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T07:31:07Z","timestamp":1784532667000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3426-4_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,21]]},"ISBN":["9789819234257","9789819234264"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3426-4_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,21]]},"assertion":[{"value":"21 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}