{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:28:08Z","timestamp":1782836888554,"version":"3.54.5"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819743988","type":"print"},{"value":"9789819743995","type":"electronic"}],"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\/978-981-97-4399-5_8","type":"book-chapter","created":{"date-parts":[[2024,7,6]],"date-time":"2024-07-06T16:01:52Z","timestamp":1720281712000},"page":"80-92","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["HiFi-WaveGAN: Generative Adversarial Network with\u00a0Auxiliary Spectrogram-Phase Loss for\u00a0High-Fidelity Singing Voice Generation"],"prefix":"10.1007","author":[{"given":"Chunhui","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ouyang","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,7]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Lu, C., Zhang, P., Yan, Y.: Self-attention based prosodic boundary prediction for Chinese speech synthesis. In: ICASSP, pp. 7035\u20137039. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682770"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Yang, B., Zhong, J., Liu, S.: Pre-trained text representations for improving front-end text processing in mandarin text-to-speech synthesis. In: INTERSPEECH, pp. 4480\u20134484 (2019)","DOI":"10.21437\/Interspeech.2019-1418"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Shen, J., et\u00a0al.: Natural TTS synthesis by conditioning WaveNet on Mel spectrogram predictions. In: ICASSP, pp. 4779\u20134783. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"8_CR4","unstructured":"Ren, Y., et al.: Fastspeech: fast, robust and controllable text to speech. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"8_CR5","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, pp. 6199\u20136203. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"8_CR6","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. Process. Syst. 33, 17022\u201317033 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR7","first-page":"22509","volume":"34","author":"X Hu","year":"2021","unstructured":"Hu, X., Li, K., Zhang, W., Luo, Y., Lemercier, J.-M., Gerkmann, T.: Speech separation using an asynchronous fully recurrent convolutional neural network. Adv. Neural. Inf. Process. Syst. 34, 22509\u201322522 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR8","unstructured":"Li, K., Yang, R., Hu, X.: An efficient encoder-decoder architecture with top-down attention for speech separation. In: ICLR (2022)"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Nishimura, M., Hashimoto, K., Oura, K., Nankaku, Y., Tokuda, K.: Singing voice synthesis based on deep neural networks. In: Interspeech, pp. 2478\u20132482 (2016)","DOI":"10.21437\/Interspeech.2016-1027"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Blaauw, M., Bonada, J.: Sequence-to-sequence singing synthesis using the feed-forward transformer. In: ICASSP, pp. 7229\u20137233. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053944"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Lu, P., Wu, J., Luan, J., Tan, X., Zhou, L.: XiaoiceSing: a high-quality and integrated singing voice synthesis system. In: Proceedings of Interspeech 2020, pp. 1306\u20131310 (2020)","DOI":"10.21437\/Interspeech.2020-1410"},{"key":"8_CR12","unstructured":"Ren, Y., et al.: FastSpeech 2: fast and high-quality end-to-end text to speech. In: ICLR (2021)"},{"key":"8_CR13","unstructured":"Li, X., et al.: Learning normality is enough: a software-based mitigation against inaudible voice attacks. In: 32nd USENIX Security Symposium (USENIX Security 2023), pp. 2455\u20132472 (2023)"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Gu, Y., et al.: Bytesing: a Chinese singing voice synthesis system using duration allocated encoder-decoder acoustic models and WaveRNN vocoders. In: ISCSLP, pp. 1\u20135. IEEE (2021)","DOI":"10.1109\/ISCSLP49672.2021.9362104"},{"issue":"7","key":"8_CR15","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.1587\/transinf.2015EDP7457","volume":"99","author":"M Morise","year":"2016","unstructured":"Morise, M., Yokomori, F., Ozawa, K.: WORLD: a vocoder-based high-quality speech synthesis system for real-time applications. IEICE Trans. Inf. Syst. 99(7), 1877\u20131884 (2016)","journal-title":"IEICE Trans. Inf. Syst."},{"key":"8_CR16","unstructured":"Kalchbrenner, N., et al.: Efficient neural audio synthesis. In: ICLR, pp. 2410\u20132419 (2018)"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Huang, R., et al.: SingGAN: generative adversarial network for high-fidelity singing voice generation. In: ACMMM (2022)","DOI":"10.1145\/3503161.3547854"},{"key":"8_CR18","unstructured":"van\u00a0den Oord, A., et al.: WaveNet: a generative model for raw audio. In: SSW (2016)"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Jang, W., Lim, D.C.Y., Yoon, J., Kim, B., Kim, J.: UnivNet: a neural vocoder with multi-resolution spectrogram discriminators for high-fidelity waveform generation. In: Interspeech (2021)","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"8_CR20","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1109\/TASLP.2019.2956145","volume":"28","author":"X Wang","year":"2019","unstructured":"Wang, X., Takaki, S., Yamagishi, J.: Neural source-filter waveform models for statistical parametric speech synthesis. IEEE\/ACM Trans. Audio Speech Lang. Process. 28, 402\u2013415 (2019)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"8_CR21","unstructured":"Wang, C., Zeng, C., He, X.: Xiaoicesing 2: a high-fidelity singing voice synthesizer based on generative adversarial network. In: Interspeech (2023)"},{"key":"8_CR22","unstructured":"Mehta, Y., et al.: NAS-bench-suite: NAS evaluation is (now) surprisingly easy. In: ICLR (2022)"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Mao, X., Li, Q., Xie, H., Lau, R.Y., Wang, Z., Paul\u00a0Smolley, S.: Least squares generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2794\u20132802 (2017)","DOI":"10.1109\/ICCV.2017.304"},{"issue":"1","key":"8_CR24","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1109\/LSP.2018.2880284","volume":"26","author":"S\u00d6 Ar\u0131k","year":"2018","unstructured":"Ar\u0131k, S.\u00d6., Jun, H., Diamos, G.: Fast spectrogram inversion using multi-head convolutional neural networks. IEEE Signal Process. Lett. 26(1), 94\u201398 (2018)","journal-title":"IEEE Signal Process. Lett."},{"key":"8_CR25","unstructured":"Kumar, K., et al.: Melgan: generative adversarial networks for conditional waveform synthesis. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"8_CR26","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Xu, S., Zhao, W., Guo, J.: RefineGAN: universally generating waveform better than ground truth with highly accurate pitch and intensity responses. In: INTERSPEECH (2022)","DOI":"10.21437\/Interspeech.2022-349"},{"key":"8_CR28","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"}],"container-title":["Lecture Notes in Computer Science","Advances in Neural Networks \u2013 ISNN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-4399-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,6]],"date-time":"2024-07-06T16:02:42Z","timestamp":1720281762000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-4399-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819743988","9789819743995"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-4399-5_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"7 July 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISNN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Weihai","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":"11 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 July 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isnn2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conference.cs.cityu.edu.hk\/isnn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}