{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T21:09:48Z","timestamp":1773868188661,"version":"3.50.1"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"DOI":"10.1186\/s13636-025-00422-5","type":"journal-article","created":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T11:52:47Z","timestamp":1761565967000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["ICRCycleGAN-VC: a robust one-to-one voice conversion method based on CycleGAN and inception-ResNet blocks"],"prefix":"10.1186","volume":"2025","author":[{"given":"Nayereh Seyed","family":"Afiuny","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9870-3676","authenticated-orcid":false,"given":"Amir","family":"Lakizadeh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"422_CR1","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1109\/TASLP.2020.3038524","volume":"29","author":"B Sisman","year":"2020","unstructured":"B. Sisman, J. Yamagishi, S. King, H. Li, An overview of voice conversion and its challenges: from statistical modeling to deep learning. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 132 (2020). https:\/\/doi.org\/10.1109\/TASLP.2020.3038524","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"422_CR2","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/0167-6393(89)90041-1","volume":"8","author":"DG Childers","year":"1989","unstructured":"D.G. Childers, K. Wu, D. Hicks, B. Yegnanarayana, Voice conversion. Speech Commun. 8, 147 (1989). https:\/\/doi.org\/10.1016\/0167-6393(89)90041-1","journal-title":"Speech Commun."},{"key":"422_CR3","doi-asserted-by":"publisher","unstructured":"A. Kain and M. W. Macon, Spectral voice conversion for text-to-speech synthesis in Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP'98 (Cat. No. 98CH36181) (IEEE, 1998), pp. 285. https:\/\/doi.org\/10.1109\/ICASSP.1998.674423","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"422_CR4","doi-asserted-by":"publisher","unstructured":"M. Zhang, X. Wang, F. Fang, H. Li, and J. Yamagishi, Joint training framework for text-to-speech and voice conversion using multi-source tacotron and wavenet. arXiv preprint arXiv:1903.12389 (2019). https:\/\/doi.org\/10.48550\/arXiv.1903.12389","DOI":"10.48550\/arXiv.1903.12389"},{"key":"422_CR5","doi-asserted-by":"publisher","first-page":"2505","DOI":"10.1109\/TASL.2012.2205241","volume":"20","author":"T Toda","year":"2012","unstructured":"T. Toda, M. Nakagiri, K. Shikano, Statistical voice conversion techniques for body-conducted unvoiced speech enhancement. IEEE Trans. Audio Speech Lang. Process. 20, 2505 (2012). https:\/\/doi.org\/10.1109\/TASL.2012.2205241","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"422_CR6","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1016\/j.specom.2011.07.007","volume":"54","author":"K Nakamura","year":"2012","unstructured":"K. Nakamura, T. Toda, H. Saruwatari, K. Shikano, Speaking-aid systems using GMM-based voice conversion for electrolaryngeal speech. Speech Commun. 54, 134 (2012). https:\/\/doi.org\/10.1016\/j.specom.2011.07.007","journal-title":"Speech Commun."},{"key":"422_CR7","doi-asserted-by":"publisher","unstructured":"T. L. New, M. Dong, P. Chan, X. Wang, B. Ma, and H. Li, Voice conversion: From spoken vowels to singing vowels in 2010 IEEE International Conference on Multimedia and Expo (IEEE, 2010), pp. 1421. https:\/\/doi.org\/10.1109\/ICME.2010.5582961","DOI":"10.1109\/ICME.2010.5582961"},{"key":"422_CR8","doi-asserted-by":"publisher","unstructured":"B. Sisman, K. Vijayan, M. Dong, and H. Li, SINGAN: Singing voice conversion with generative adversarial networks in 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) (IEEE, 2019), pp. 112. https:\/\/doi.org\/10.1109\/APSIPAASC47483.2019.9023162","DOI":"10.1109\/APSIPAASC47483.2019.9023162"},{"key":"422_CR9","doi-asserted-by":"publisher","DOI":"10.3390\/app13053100","volume":"13","author":"T Walczyna","year":"2023","unstructured":"T. Walczyna, Z. Piotrowski, Overview of voice conversion methods based on deep learning. Appl. Sci. 13, 3100 (2023). https:\/\/doi.org\/10.3390\/app13053100","journal-title":"Appl. Sci."},{"key":"422_CR10","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.specom.2020.05.004","volume":"122","author":"M Zhang","year":"2020","unstructured":"M. Zhang, B. Sisman, L. Zhao, H. Li, Deepconversion: voice conversion with limited parallel training data. Speech Commun. 122, 31 (2020). https:\/\/doi.org\/10.1016\/j.specom.2020.05.004","journal-title":"Speech Commun."},{"key":"422_CR11","doi-asserted-by":"publisher","unstructured":"S. Dhar, N. D. Jana, and S. Das, Generative adversarial network based voice conversion: techniques, challenges, and recent advancements. arXiv preprint arXiv:2504.19197 (2025). https:\/\/doi.org\/10.48550\/arXiv.2504.19197","DOI":"10.48550\/arXiv.2504.19197"},{"key":"422_CR12","doi-asserted-by":"publisher","unstructured":"T. Kaneko, H. Kameoka, K. Tanaka, and N. Hojo, Stargan-vc2: Rethinking conditional methods for stargan-based voice conversion. arXiv preprint arXiv:1907.12279 (2019). https:\/\/doi.org\/10.48550\/arXiv.1907.12279","DOI":"10.48550\/arXiv.1907.12279"},{"key":"422_CR13","doi-asserted-by":"publisher","unstructured":"V. Popov, I. Vovk, V. Gogoryan, T. Sadekova, M. Kudinov, and J. Wei, Diffusion-based voice conversion with fast maximum likelihood sampling scheme. arXiv preprint arXiv:2109.13821 (2021). https:\/\/doi.org\/10.48550\/arXiv.2109.13821","DOI":"10.48550\/arXiv.2109.13821"},{"key":"422_CR14","doi-asserted-by":"publisher","unstructured":"D. Wang, L. Deng, Y. T. Yeung, X. Chen, X. Liu, and H. Meng, Vqmivc: Vector quantization and mutual information-based unsupervised speech representation disentanglement for one-shot voice conversion. arXiv preprint arXiv:2106.10132 (2021). https:\/\/doi.org\/10.48550\/arXiv.2106.10132","DOI":"10.48550\/arXiv.2106.10132"},{"key":"422_CR15","doi-asserted-by":"publisher","unstructured":"J. Li, W. Tu, and L. Xiao, Freevc: Towards high-quality text-free one-shot voice conversion in ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2023), pp. 1. https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10095191","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"422_CR16","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1109\/89.661472","volume":"6","author":"Y Stylianou","year":"1998","unstructured":"Y. Stylianou, O. Capp\u00e9, E. Moulines, Continuous probabilistic transform for voice conversion. IEEE Trans. Speech Audio Process. 6, 131 (1998). https:\/\/doi.org\/10.1109\/89.661472","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"422_CR17","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1109\/TASL.2007.907344","volume":"15","author":"T Toda","year":"2007","unstructured":"T. Toda, A.W. Black, K. Tokuda, Voice conversion based on maximum-likelihood estimation of spectral parameter trajectory. IEEE Trans. Audio Speech Lang. Process. 15, 2222 (2007). https:\/\/doi.org\/10.1109\/TASL.2007.907344","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"422_CR18","doi-asserted-by":"publisher","first-page":"912","DOI":"10.1109\/TASL.2010.2041699","volume":"18","author":"E Helander","year":"2010","unstructured":"E. Helander, T. Virtanen, J. Nurminen, M. Gabbouj, Voice conversion using partial least squares regression. IEEE Trans. Audio Speech Lang. Process. 18, 912 (2010). https:\/\/doi.org\/10.1109\/TASL.2010.2041699","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"422_CR19","doi-asserted-by":"publisher","unstructured":"S. H. Mohammadi and A. Kain, Voice conversion using deep neural networks with speaker-independent pre-training in 2014 IEEE Spoken Language Technology Workshop (SLT) (IEEE, 2014), pp. 19. https:\/\/doi.org\/10.1109\/SLT.2014.7078543","DOI":"10.1109\/SLT.2014.7078543"},{"key":"422_CR20","doi-asserted-by":"publisher","first-page":"1925","DOI":"10.1587\/transinf.2017EDL8034","volume":"100","author":"Y Saito","year":"2017","unstructured":"Y. Saito, S. Takamichi, H. Saruwatari, Voice conversion using input-to-output highway networks. IEICE Trans. Inf. Syst. 100, 1925 (2017). https:\/\/doi.org\/10.1587\/transinf.2017EDL8034","journal-title":"IEICE Trans. Inf. Syst."},{"key":"422_CR21","doi-asserted-by":"publisher","unstructured":"L. Sun, S. Kang, K. Li, and H. Meng, Voice conversion using deep bidirectional long short-term memory based recurrent neural networks in 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP) (IEEE, 2015), pp. 4869. https:\/\/doi.org\/10.1109\/ICASSP.2015.7178896","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"422_CR22","doi-asserted-by":"publisher","unstructured":"T. Kaneko, H. Kameoka, K. Hiramatsu, and K. Kashino, Sequence-to-sequence voice conversion with similarity metric learned using generative adversarial networks in Interspeech2017), pp. 1283. https:\/\/doi.org\/10.21437\/Interspeech.2017-970","DOI":"10.21437\/Interspeech.2017-970"},{"key":"422_CR23","doi-asserted-by":"publisher","unstructured":"Y. Alaa, M. Alfonse, and M. M. Aref, A survey on generative adversarial networks based models for many-to-many non-parallel voice conversion in 2022 5th International Conference on Computing and Informatics (ICCI) (IEEE, 2022), pp. 221. https:\/\/doi.org\/10.1109\/ICCI54321.2022.9756059","DOI":"10.1109\/ICCI54321.2022.9756059"},{"key":"422_CR24","doi-asserted-by":"publisher","unstructured":"J.-Y. Zhu, T. Park, P. Isola, and A. A. Efros, Unpaired image-to-image translation using cycle-consistent adversarial networks in Proceedings of the IEEE international conference on computer vision2017), pp. 2223. https:\/\/doi.org\/10.48550\/arXiv.1703.10593","DOI":"10.48550\/arXiv.1703.10593"},{"key":"422_CR25","doi-asserted-by":"publisher","unstructured":"T. Kaneko and H. Kameoka, Cyclegan-vc: Non-parallel voice conversion using cycle-consistent adversarial networks in 2018 26th European Signal Processing Conference (EUSIPCO) (IEEE, 2018), pp. 2100. https:\/\/doi.org\/10.23919\/EUSIPCO.2018.8553236","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"422_CR26","doi-asserted-by":"publisher","unstructured":"T. Kaneko, H. Kameoka, K. Tanaka, and N. Hojo, Cyclegan-vc2: Improved cyclegan-based non-parallel voice conversion in ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2019), pp. 6820. https:\/\/doi.org\/10.1109\/ICASSP.2019.8682897","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"422_CR27","doi-asserted-by":"publisher","unstructured":"T. Kaneko, H. Kameoka, K. Tanaka, and N. Hojo, CycleGAN-VC3: Examining and improving CycleGAN-VCs for mel-spectrogram conversion. arXiv preprint arXiv:2010.11672 (2020). https:\/\/doi.org\/10.48550\/arXiv.2010.11672","DOI":"10.48550\/arXiv.2010.11672"},{"key":"422_CR28","doi-asserted-by":"publisher","unstructured":"T. Kaneko, H. Kameoka, K. Tanaka, and N. Hojo, Maskcyclegan-VC: Learning Non-Parallel Voice Conversion with Filling in Frames in ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2021), pp. 5919. https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414851","DOI":"10.1109\/ICASSP39728.2021.9414851"},{"key":"422_CR29","doi-asserted-by":"publisher","unstructured":"B. Nguyen and F. Cardinaux, Nvc-net: End-to-end adversarial voice conversion in ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2022), pp. 7012. https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9747020","DOI":"10.1109\/ICASSP43922.2022.9747020"},{"key":"422_CR30","doi-asserted-by":"publisher","unstructured":"D. Ke, W. Yao, R. Hu, L. Huang, Q. Luo, and W. Shu, StyleFormerGAN-VC: Improving Effect of few shot Cross-Lingual Voice Conversion Using VAE-StarGAN and Attention-AdaIN in 2022 IEEE\/ACIS 23rd International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel\/Distributed Computing (SNPD) (IEEE, 2022), pp. 235. https:\/\/doi.org\/10.1109\/SNPD54884.2022.10051811","DOI":"10.1109\/SNPD54884.2022.10051811"},{"key":"422_CR31","unstructured":"J. Kim, J. Kong, and J. Son, Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech in International Conference on Machine Learning (PMLR, 2021), pp. 5530.\u00a0"},{"key":"422_CR32","doi-asserted-by":"publisher","unstructured":"H. Guo, C. Liu, C. T. Ishi, and H. Ishiguro, QuickVC: Any-to-many voice conversion using inverse short-time fourier transform for faster conversion. arXiv preprint arXiv:2302.08296 (2023). https:\/\/doi.org\/10.48550\/arXiv.2302.08296","DOI":"10.48550\/arXiv.2302.08296"},{"key":"422_CR33","doi-asserted-by":"publisher","unstructured":"S. Bahaadini, H. Sameti, and S. Khorram, Implementation and evaluation of statistical parametric speech synthesis methods for the Persian language in 2011 IEEE International Workshop on Machine Learning for Signal Processing (IEEE, 2011), pp. 1. https:\/\/doi.org\/10.1109\/MLSP.2011.6064608","DOI":"10.1109\/MLSP.2011.6064608"},{"key":"422_CR34","unstructured":"S. Karimi, F. Scholer, and A. Turpin, Collapsed consonant and vowel models: New approaches for English-Persian transliteration and back-transliteration in Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics2007), pp. 648."},{"key":"422_CR35","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1006\/jmla.1996.2503","volume":"36","author":"SM Davis","year":"1997","unstructured":"S.M. Davis, M.H. Kelly, Knowledge of the English noun\u2013verb stress difference by native and nonnative speakers. J. Mem. Lang. 36, 445 (1997). https:\/\/doi.org\/10.1006\/jmla.1996.2503","journal-title":"J. Mem. Lang."},{"key":"422_CR36","doi-asserted-by":"publisher","unstructured":"Q. Dabouis and J.-M. Fournier, The Stress Patterns of English Verbs: Syllable Weight and Morphology. New perspectives on English word stress, 154 (2023). https:\/\/doi.org\/10.1006\/jmla.1996.2503","DOI":"10.1006\/jmla.1996.2503"},{"key":"422_CR37","doi-asserted-by":"crossref","unstructured":"H. Sheikhzadeh, A. Eshkevari, M. Khayatian, M. R. Sadigh, and S. M. Ahadi, Farsi language prosodic structure, research and implementation using a speech synthesizer in EUROSPEECH1999), pp. 1647.","DOI":"10.21437\/Eurospeech.1999-432"},{"key":"422_CR38","doi-asserted-by":"publisher","unstructured":"C. Szegedy, S. Ioffe, V. Vanhoucke, and A. Alemi, Inception-v4, inception-resnet and the impact of residual connections on learning in Proceedings of the AAAI conference on artificial intelligence2017). https:\/\/doi.org\/10.1609\/aaai.v31i1.11231","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"422_CR39","doi-asserted-by":"publisher","unstructured":"D. Pathak, P. Krahenbuhl, J. Donahue, T. Darrell, and A. A. Efros, Context encoders: Feature learning by inpainting in Proceedings of the IEEE conference on computer vision and pattern recognition2016), pp. 2536. https:\/\/doi.org\/10.1109\/CVPR.2016.278","DOI":"10.1109\/CVPR.2016.278"},{"key":"422_CR40","doi-asserted-by":"publisher","unstructured":"W. Fedus, I. Goodfellow, and A. M. Dai, Maskgan: better text generation via filling in the_. arXiv preprint arXiv:1801.07736 (2018). https:\/\/doi.org\/10.48550\/arXiv.1801.07736","DOI":"10.48550\/arXiv.1801.07736"},{"key":"422_CR41","doi-asserted-by":"publisher","unstructured":"J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, Bert: pre-training of deep bidirectional transformers for language understanding in Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers)2019), pp. 4171. https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"422_CR42","doi-asserted-by":"publisher","unstructured":"Y. N. Dauphin, A. Fan, M. Auli, and D. Grangier, Language modeling with gated convolutional networks in International conference on machine learning (PMLR, 2017), pp. 933. https:\/\/doi.org\/10.48550\/arXiv.1612.08083","DOI":"10.48550\/arXiv.1612.08083"},{"key":"422_CR43","doi-asserted-by":"publisher","unstructured":"K. Kumar, R. Kumar, T. de Boissiere, L. Gestin, W. Z. Teoh, J. Sotelo, A. de Br\u00e9bisson, Y. Bengio, and A. C. Courville, Melgan: Generative adversarial networks for conditional waveform synthesis. Advances in neural information processing systems 32 (2019). https:\/\/doi.org\/10.48550\/arXiv.1910.06711","DOI":"10.48550\/arXiv.1910.06711"},{"key":"422_CR44","doi-asserted-by":"publisher","unstructured":"X. Mao, Q. Li, H. Xie, R. Y. Lau, Z. Wang, and S. Paul Smolley, Least squares generative adversarial networks in Proceedings of the IEEE international conference on computer vision2017), pp. 2794. https:\/\/doi.org\/10.48550\/arXiv.1611.04076","DOI":"10.48550\/arXiv.1611.04076"},{"key":"422_CR45","unstructured":"M. Bijankhan, J. Sheikhzadegan, and M. R. Roohani, FARSDAT-The speech database of Farsi spoken language (Proccedings Australian Conference on Speech Science and Technology, 1994)."},{"key":"422_CR46","doi-asserted-by":"publisher","unstructured":"J. Lorenzo-Trueba, J. Yamagishi, T. Toda, D. Saito, F. Villavicencio, T. Kinnunen, and Z. Ling, The voice conversion challenge 2018: Database and results. The Centre for Speech Technology Research, The University of Edinburgh, UK (2018). https:\/\/doi.org\/10.7488\/ds\/2337","DOI":"10.7488\/ds\/2337"},{"key":"422_CR47","doi-asserted-by":"publisher","unstructured":"Y. Zhao, W.-C. Huang, X. Tian, J. Yamagishi, R. K. Das, T. Kinnunen, Z. Ling, and T. Toda, Voice conversion challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversion. arXiv preprint arXiv:2008.12527 (2020). https:\/\/doi.org\/10.48550\/arXiv.2008.12527","DOI":"10.48550\/arXiv.2008.12527"},{"key":"422_CR48","unstructured":"J. Yamagishi, C. Veaux, and K. MacDonald, CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92). University of Edinburgh. The Centre for Speech Technology Research (CSTR), 271 (2019)."},{"key":"422_CR49","doi-asserted-by":"publisher","unstructured":"A. Radford, J. W. Kim, T. Xu, G. Brockman, C. McLeavey, and I. Sutskever, Robust speech recognition via large-scale weak supervision in International conference on machine learning (PMLR, 2023), pp. 28492. https:\/\/doi.org\/10.48550\/arXiv.2212.04356","DOI":"10.48550\/arXiv.2212.04356"},{"key":"422_CR50","doi-asserted-by":"publisher","unstructured":"S. Seshadri, L. Juvela, J. Yamagishi, O. R\u00e4s\u00e4nen, and P. Alku, Cycle-consistent adversarial networks for non-parallel vocal effort based speaking style conversion in ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2019), pp. 6835. https:\/\/doi.org\/10.1109\/ICASSP.2019.8682648","DOI":"10.1109\/ICASSP.2019.8682648"},{"key":"422_CR51","doi-asserted-by":"publisher","unstructured":"R. Ferro, N. Obin, and A. Roebel, Cyclegan voice conversion of spectral envelopes using adversarial weights in 2020 28th European Signal Processing Conference (EUSIPCO) (IEEE, 2021), pp. 406. https:\/\/doi.org\/10.23919\/Eusipco47968.2020.9287643","DOI":"10.23919\/Eusipco47968.2020.9287643"},{"key":"422_CR52","doi-asserted-by":"publisher","unstructured":"F. Fang, J. Yamagishi, I. Echizen, and J. Lorenzo-Trueba, High-quality nonparallel voice conversion based on cycle-consistent adversarial network in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2018), pp. 5279. https:\/\/doi.org\/10.1109\/ICASSP.2018.8462342","DOI":"10.1109\/ICASSP.2018.8462342"},{"key":"422_CR53","doi-asserted-by":"publisher","unstructured":"S. Lee, B. Ko, K. Lee, I.-C. Yoo, and D. Yook, Many-to-many voice conversion using conditional cycle-consistent adversarial networks in ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2020), pp. 6279. https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053726","DOI":"10.1109\/ICASSP40776.2020.9053726"}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-025-00422-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13636-025-00422-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-025-00422-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T11:52:51Z","timestamp":1761565971000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13636-025-00422-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":53,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["422"],"URL":"https:\/\/doi.org\/10.1186\/s13636-025-00422-5","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"30 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"37"}}