{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T12:11:26Z","timestamp":1743077486336,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819756650"},{"type":"electronic","value":"9789819756667"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-5666-7_28","type":"book-chapter","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T20:37:45Z","timestamp":1722544665000},"page":"330-342","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["NVCGAN: Leveraging Generative Adversarial Networks for Robust Voice Conversion"],"prefix":"10.1007","author":[{"given":"Guoyu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingrui","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhao","family":"Bi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangcheng","family":"Dongye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Jing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiguo","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,1]]},"reference":[{"issue":"4","key":"28_CR1","doi-asserted-by":"publisher","first-page":"1313","DOI":"10.1109\/TASL.2011.2177820","volume":"20","author":"E Godoy","year":"2011","unstructured":"Godoy, E., Rosec, O., Chonavel, T.: Voice conversion using dynamic frequency warping with amplitude scaling, for parallel or nonparallel corpora. IEEE Trans. Audio Speech Lang. Process. 20(4), 1313\u20131323 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Toda, Tomoki, et al.: The voice conversion challenge 2016. In: Interspeech, vol. 2016 (2016)","DOI":"10.21437\/Interspeech.2016-1066"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Stylianou, Y., Capp\u00e9, O., Moulines, E.: Continuous probabilistic transform for voice conversion. IEEE Trans. Speech Audio Process. 6(2), 131\u2013142 (1998)","DOI":"10.1109\/89.661472"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Erro, D., Navas, E., Hernaez, I.: Parametric voice conversion based on bilinear frequency warping plus amplitude scaling. IEEE Trans. Audio Speech Lang. Process. 21(3), 556\u2013566 (2012)","DOI":"10.1109\/TASL.2012.2227735"},{"key":"28_CR5","unstructured":"Yanping, L., et al.: Voice conversion based on variational autoencoders and auxiliary classifier generative adversarial networks under non-parallel text. J. Fudan Univ. Nat. Sci. Ed. 59(3), 322\u2013329 (2020)"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Daniel, E., Moreno, A., Bonafonte, A.: INCA algorithm for training voice conversion systems from nonparallel corpora. IEEE Trans. Audio Speech Lang. Process. 18(5), 944\u2013953 (2009)","DOI":"10.1109\/TASL.2009.2038669"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Xie, F.-L., Soong, F.K., Li, H.: A KL divergence and DNN approach to cross-lingual TTS. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472732"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Zhao, X., et al.: Disentangling content and fine-grained prosody information via hybrid ASR bottleneck features for voice conversion. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747625"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Toda, T.: Augmented speech production based on real-time statistical voice conversion. In: 2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP). IEEE (2014)","DOI":"10.1109\/GlobalSIP.2014.7032186"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Kinnunen, T., et al.: Non-parallel voice conversion using i-vector PLDA: towards unifying speaker verification and transformation. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7953215"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Sun, L., et al.: Phonetic posteriorgrams for many-to-one voice conversion without parallel data training. In: 2016 IEEE International Conference on Multimedia and Expo (ICME). IEEE (2016)","DOI":"10.1109\/ICME.2016.7552917"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Hsu, C.-C., et al.: Voice conversion from non-parallel corpora using variational auto-encoder. In: 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA). IEEE (2016)","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"28_CR13","unstructured":"Serr\u00e0, J., Pascual, S., Perales, C.S.: Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"28_CR14","unstructured":"Goodfellow, L., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Kaneko, T., Kameoka, H.: Parallel-data-free voice conversion using cycle-consistent adversarial networks (2017). arXiv preprint arXiv:1711.11293","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Zhu, J.-Y., et al.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Hsu, C.-C., et al.: Voice conversion from unaligned corpora using variational autoencoding wasserstein generative adversarial networks (2017). arXiv preprint arXiv:1704.00849","DOI":"10.21437\/Interspeech.2017-63"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Yamamoto, R., Song, E., Kim, J.-M.: Parallel WaveGAN: a fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Kameoka, H., et al.: StarGAN-VC: non-parallel many-to-many voice conversion using star generative adversarial networks. In: 2018 IEEE Spoken Language Technology Workshop (SLT). IEEE (2018)","DOI":"10.1109\/SLT.2018.8639535"},{"key":"28_CR20","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning. PMLR (2017)"},{"key":"28_CR21","unstructured":"Targ, S., Almeida, D., Lyman, K.: Resnet in resnet: Generalizing residual architectures (2016). arXiv preprint arXiv:1603.08029"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Jiang, B., Dong, Q., Liu, G.: A method of phonemic annotation for Chinese dialects based on a deep learning model with adaptive temporal attention and a feature disentangling structure. Comput. Speech Lang. 86, 101624 (2024)","DOI":"10.1016\/j.csl.2024.101624"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Perraudin, N., Balazs, P., S\u00f8ndergaard, P.L.: A fast Griffin-Lim algorithm. In: 2013 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics. IEEE (2013)","DOI":"10.1109\/WASPAA.2013.6701851"},{"key":"28_CR24","unstructured":"Kong, J., Kim, J., Bae, J.: HiFi-GAN: generative adversarial networks for efficient and high fidelity speech synthesis. Adv. Neural Inf. Process. Syst. 33, 17022\u201317033 (2020)"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: EFRNet: efficient feature reuse network for real-time semantic segmentation. Neural Process. Lett. 54(6), 4647\u20134659 (2022)","DOI":"10.1007\/s11063-022-10740-w"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A., Zisserman, A.: VoxCeleb2: Deep speaker recognition. (2018). arXiv preprint arXiv:1806.05622","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Fu, Y., et al.: AISHELL-4: An open source dataset for speech enhancement, separation, recognition and speaker diarization in conference scenario (2021). arXiv preprint arXiv:2104.03603","DOI":"10.21437\/Interspeech.2021-1397"},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Tran, T., et al.: Separate sound into STFT frames to eliminate sound noise frames in sound classification. In: 2021 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE (2021)","DOI":"10.1109\/SSCI50451.2021.9660125"},{"key":"28_CR29","doi-asserted-by":"crossref","unstructured":"Gulati, A., et al.: Conformer: Convolution-augmented transformer for speech recognition (2020). arXiv preprint arXiv:2005.08100","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Toda, T., Tokuda, K.: A speech parameter generation algorithm considering global variance for HMM-based speech synthesis. IEICE Trans. Inf. Syst. 90(5), 816\u2013824 (2007)","DOI":"10.1093\/ietisy\/e90-d.5.816"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Wan, L., et al.: Generalized end-to-end loss for speaker verification. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"28_CR32","doi-asserted-by":"crossref","unstructured":"Kubichek, R.: Mel-cepstral distance measure for objective speech quality assessment. In: Proceedings of IEEE Pacific Rim Conference on Communications Computers and Signal Processing, vol. 1, pp. 125\u2013128 (1993)","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Chen, Y.-H., et al.: AGAIN-VC: a one-shot voice conversion using activation guidance and adaptive instance normalization. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"28_CR34","unstructured":"Qian, K., et al.: AutoVC: Zero-shot voice style transfer with only autoencoder loss. In: International Conference on Machine Learning. PMLR (2019)"},{"key":"28_CR35","doi-asserted-by":"crossref","unstructured":"Lin, J.-H., et al.: S2VC: A framework for any-to-any voice conversion with self-supervised pretrained representations (2021). arXiv preprint arXiv:2104.02901","DOI":"10.21437\/Interspeech.2021-1356"}],"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\/978-981-97-5666-7_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T16:24:45Z","timestamp":1732551885000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5666-7_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819756650","9789819756667"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5666-7_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 August 2024","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":"Tianjin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}