{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T17:12:53Z","timestamp":1787505173495,"version":"build-2736575974"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T00:00:00Z","timestamp":1750636800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T00:00:00Z","timestamp":1750636800000},"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. King Saud Univ. Comput. Inf. Sci."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s44443-025-00082-7","type":"journal-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T04:03:14Z","timestamp":1750651394000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Emotion transfer in audio using mel-cepstral representation and CycleGANs"],"prefix":"10.1007","volume":"37","author":[{"given":"Guijin","family":"Han","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2335-9040","authenticated-orcid":false,"given":"Junzhe","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiming","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,23]]},"reference":[{"key":"82_CR1","doi-asserted-by":"publisher","first-page":"122136","DOI":"10.1109\/ACCESS.2022.3223444","volume":"10","author":"ZK Abdul","year":"2022","unstructured":"Abdul ZK, Al-Talabani AK (2022) Mel frequency cepstral coefficient and its applications: A review. IEEE Access. 10:122136\u2013122158. https:\/\/doi.org\/10.1109\/ACCESS.2022.3223444","journal-title":"IEEE Access."},{"key":"82_CR2","doi-asserted-by":"publisher","unstructured":"Ba JL, Kiros JR, Hinton GE (2016) Layer Normalization. https:\/\/doi.org\/10.48550\/arXiv.1607.06450","DOI":"10.48550\/arXiv.1607.06450"},{"key":"82_CR3","doi-asserted-by":"publisher","unstructured":"Choi Y, Choi M, Kim M, Ha J-W, Kim S, Choo J (2018) StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation. https:\/\/doi.org\/10.48550\/arXiv.1711.09020","DOI":"10.48550\/arXiv.1711.09020"},{"key":"82_CR4","doi-asserted-by":"publisher","unstructured":"Chung J, Gulcehre C, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.1412.3555","DOI":"10.48550\/arXiv.1412.3555"},{"key":"82_CR5","doi-asserted-by":"publisher","unstructured":"Dauphin YN, Fan A, Auli M, Grangier D (2017) Language modeling with gated convolutional networks. In: International conference on machine learning. PML, pp 933\u2013941. https:\/\/doi.org\/10.48550\/arXiv.1612.08083","DOI":"10.48550\/arXiv.1612.08083"},{"key":"82_CR6","doi-asserted-by":"publisher","unstructured":"Fan W, Xu X, Xing X, Huang D (2020) Adaptive domain-aware representation learning for speech emotion recognition. In: Interspeech, pp 4089\u20134093. https:\/\/doi.org\/10.21437\/Interspeech.2020-2572","DOI":"10.21437\/Interspeech.2020-2572"},{"key":"82_CR7","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"82_CR8","doi-asserted-by":"publisher","unstructured":"Huang X, Belongie S (2017) Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE international conference on computer vision, pp 1501\u20131510. https:\/\/doi.org\/10.48550\/arXiv.1703.06868","DOI":"10.48550\/arXiv.1703.06868"},{"key":"82_CR9","doi-asserted-by":"publisher","unstructured":"Huang X, Liu M-Y, Belongie S, Kautz J (2018) Multimodal Unsupervised Image-to-Image Translation. https:\/\/doi.org\/10.48550\/arXiv.1804.04732","DOI":"10.48550\/arXiv.1804.04732"},{"key":"82_CR10","doi-asserted-by":"publisher","unstructured":"Isola P, Zhu J-Y, Zhou T, Efros AA (2017) Image-to-image translation with conditional adversarial networks. In: 2017 IEEE Conference on computer vision and pattern recognition (CVPR), pp 5967\u20135976. https:\/\/doi.org\/10.1109\/CVPR.2017.632","DOI":"10.1109\/CVPR.2017.632"},{"issue":"1","key":"82_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10115-011-0463-8","volume":"33","author":"F Kamiran","year":"2012","unstructured":"Kamiran F, Calders T (2012) Data preprocessing techniques for classification without discrimination. Knowl Inf Syst 33(1):1\u201333. https:\/\/doi.org\/10.1007\/s10115-011-0463-8","journal-title":"Knowl Inf Syst"},{"key":"82_CR12","doi-asserted-by":"publisher","unstructured":"Karnewar A, Wang O (2020) Msg-gan: Multi-scale gradients for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7799\u20137808. https:\/\/doi.org\/10.48550\/arXiv.1903.06048","DOI":"10.48550\/arXiv.1903.06048"},{"key":"82_CR13","doi-asserted-by":"publisher","unstructured":"Kim J, Kong J, Son J (2021) Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech. In: International conference on machine learning. PMLR, pp 5530\u20135540. https:\/\/doi.org\/10.48550\/arXiv.2106.06103","DOI":"10.48550\/arXiv.2106.06103"},{"key":"82_CR14","doi-asserted-by":"publisher","unstructured":"Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.1412.6980","DOI":"10.48550\/arXiv.1412.6980"},{"key":"82_CR15","doi-asserted-by":"publisher","unstructured":"Li Q, Jia X, Zhou J, Shen L, Duan J (2024) Rediscovering bce loss for uniform classification. arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.2403.07289","DOI":"10.48550\/arXiv.2403.07289"},{"key":"82_CR16","doi-asserted-by":"publisher","unstructured":"Liu R, Sisman B, Li H (2021) Reinforcement learning for emotional text-to-speech synthesis with improved emotion discriminability. arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.2104.01408","DOI":"10.48550\/arXiv.2104.01408"},{"key":"82_CR17","doi-asserted-by":"publisher","unstructured":"Loshchilov I, Hutter F (2016) Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.1608.03983","DOI":"10.48550\/arXiv.1608.03983"},{"key":"82_CR18","doi-asserted-by":"publisher","unstructured":"Mariani G, Tallini I, Postolache E, Mancusi M, Cosmo L, Rodol\u00e0 E (2023) Multi-source diffusion models for simultaneous music generation and separation. arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.2302.02257","DOI":"10.48550\/arXiv.2302.02257"},{"key":"82_CR19","doi-asserted-by":"publisher","unstructured":"Micikevicius P, Narang S, Alben J, Diamos G, Elsen E, Garcia D, Ginsburg B, Houston M, Kuchaiev O, Venkatesh G et al (2017) Mixed precision training. arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.1710.03740","DOI":"10.48550\/arXiv.1710.03740"},{"key":"82_CR20","doi-asserted-by":"publisher","unstructured":"Min D, Lee DB, Yang E, Hwang SJ (2021) Meta-stylespeech: Multi-speaker adaptive text-to-speech generation. In: International conference on machine learning. PMLR, pp 7748\u20137759 . https:\/\/doi.org\/10.48550\/arXiv.2106.03153","DOI":"10.48550\/arXiv.2106.03153"},{"key":"82_CR21","doi-asserted-by":"publisher","unstructured":"Mirza M, Osindero S (2014) Conditional Generative Adversarial Nets. https:\/\/doi.org\/10.48550\/arXiv.1411.1784","DOI":"10.48550\/arXiv.1411.1784"},{"key":"82_CR22","doi-asserted-by":"publisher","unstructured":"OhSangshin, UmSe-Yun, JangInseon, Hyun, KangHong-Goo A (2019) Determination of representative emotional style of speech based on k-means algorithm. The Journal of the Acoustical Society of Korea. 38(5):614\u2013620. https:\/\/doi.org\/10.7776\/ASK.2019.38.5.614","DOI":"10.7776\/ASK.2019.38.5.614"},{"key":"82_CR23","doi-asserted-by":"publisher","unstructured":"Sahu B, Palo HK, Shrotriya S (2021) Speech emotion recognition using k-means apriori feature selection algorithm. In: 2021 International conference in advances in power, signal, and information technology (APSIT). IEEE, pp 1\u20134. https:\/\/doi.org\/10.1109\/APSIT52773.2021.9641360","DOI":"10.1109\/APSIT52773.2021.9641360"},{"key":"82_CR24","doi-asserted-by":"publisher","unstructured":"Shi Z (2021) A survey on audio synthesis and audio-visual multimodal processing. arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.2108.00443","DOI":"10.48550\/arXiv.2108.00443"},{"key":"82_CR25","unstructured":"Shui Y (2025) Normalization in Deep Learning. Web Article. https:\/\/syhya.github.io\/posts\/2025-02-01-normalization"},{"key":"82_CR26","doi-asserted-by":"publisher","unstructured":"Song K, Xue H, Wang X, Cong J, Zhang Y, Xie L, Yang B, Zhang X, Su D (2022) Adavits: Tiny vits for low computing resource speaker adaptation. In: 2022 13th International symposium on chinese spoken language processing (ISCSLP). IEEE, pp 319\u2013323. https:\/\/doi.org\/10.1109\/ISCSLP57327.2022.10037585","DOI":"10.1109\/ISCSLP57327.2022.10037585"},{"key":"82_CR27","doi-asserted-by":"publisher","unstructured":"Tan X, Qin T, Soong F, Liu T-Y (2021) A survey on neural speech synthesis. arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.2106.15561","DOI":"10.48550\/arXiv.2106.15561"},{"key":"82_CR28","doi-asserted-by":"publisher","DOI":"10.1145\/3530811","author":"Y Tay","year":"2022","unstructured":"Tay Y, Dehghani M, Bahri D, Metzler D (2022). Efficient Transformers: A Survey. https:\/\/doi.org\/10.1145\/3530811","journal-title":"Efficient Transformers: A Survey"},{"key":"82_CR29","doi-asserted-by":"publisher","unstructured":"Ulyanov D, Vedaldi A, Lempitsky V (2017) Instance Normalization: The Missing Ingredient for Fast Stylization. https:\/\/doi.org\/10.48550\/arXiv.1607.08022","DOI":"10.48550\/arXiv.1607.08022"},{"key":"82_CR30","doi-asserted-by":"publisher","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Advances in neural information processing systems, 30. https:\/\/doi.org\/10.48550\/arXiv.1706.03762","DOI":"10.48550\/arXiv.1706.03762"},{"key":"82_CR31","doi-asserted-by":"publisher","unstructured":"Wu D-Y, Chen Y-H, Lee H-Y (2020) Vqvc+: One-shot voice conversion by vector quantization and u-net architecture. arXiv preprint arXiv https:\/\/doi.org\/10.48550\/arXiv.2006.04154","DOI":"10.48550\/arXiv.2006.04154"},{"key":"82_CR32","doi-asserted-by":"publisher","unstructured":"Yi Z, Zhang H, Tan P, Gong M (2018) DualGAN: Unsupervised Dual Learning for Image-to-Image Translation. https:\/\/doi.org\/10.1109\/ICCV.2017.310","DOI":"10.1109\/ICCV.2017.310"},{"key":"82_CR33","doi-asserted-by":"publisher","unstructured":"Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions. arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.1511.07122","DOI":"10.48550\/arXiv.1511.07122"},{"key":"82_CR34","doi-asserted-by":"publisher","unstructured":"Zhang Z, Zhou L, Wang C, Chen S, Wu Y, Liu S, Chen Z, Liu Y, Wang H, Li J et al (2023) Speak foreign languages with your own\u00a0voice: Cross-lingual neural codec language modeling. https:\/\/doi.org\/10.48550\/arXiv.2303.03926","DOI":"10.48550\/arXiv.2303.03926"},{"key":"82_CR35","doi-asserted-by":"publisher","unstructured":"Zhang X, Zou Y, Shi W (2017) Dilated convolution neural network with leakyrelu for environmental sound classification. In: 2017 22nd International conference on digital signal processing (DSP). Ieee, pp 1\u20135. https:\/\/doi.org\/10.1109\/ICDSP.2017.8096153","DOI":"10.1109\/ICDSP.2017.8096153"},{"key":"82_CR36","doi-asserted-by":"publisher","unstructured":"Zhou H, Liu K, Shenzhen P (2020) Speech emotion recognition with discriminative feature learning. In: Interspeech, pp 4094\u20134097. https:\/\/doi.org\/10.21437\/Interspeech.2020-2237","DOI":"10.21437\/Interspeech.2020-2237"},{"key":"82_CR37","doi-asserted-by":"publisher","unstructured":"Zhu J-Y, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 2223\u20132232. https:\/\/doi.org\/10.48550\/arXiv.1703.10593","DOI":"10.48550\/arXiv.1703.10593"}],"container-title":["Journal of King Saud University Computer and Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-025-00082-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44443-025-00082-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-025-00082-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T17:27:44Z","timestamp":1753723664000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44443-025-00082-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,23]]},"references-count":37,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["82"],"URL":"https:\/\/doi.org\/10.1007\/s44443-025-00082-7","relation":{},"ISSN":["1319-1578","2213-1248"],"issn-type":[{"value":"1319-1578","type":"print"},{"value":"2213-1248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,23]]},"assertion":[{"value":"18 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"79"}}