{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T16:44:47Z","timestamp":1758905087136,"version":"3.40.3"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031783463"},{"type":"electronic","value":"9783031783470"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-78347-0_16","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T14:53:56Z","timestamp":1733064836000},"page":"233-249","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["KunquDB: An Attempt for\u00a0Speaker Verification in\u00a0the\u00a0Chinese Opera Scenario"],"prefix":"10.1007","author":[{"given":"Huali","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuke","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"16_CR1","unstructured":"Black, D.A., Li, M., Tian, M.: Automatic identification of emotional cues in Chinese opera singing. In: ICMPC, Seoul, South Korea (2014)"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Brown, A., Huh, J., Nagrani, A., Chung, J.S., Zisserman, A.: Playing a part: speaker verification at the movies. In: Proceedings of the ICASSP, pp. 6174\u20136178 (2021)","DOI":"10.1109\/ICASSP39728.2021.9413815"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Cai, D., Cai, W., Li, M.: Within-sample variability-invariant loss for robust speaker recognition under noisy environments. In: Proceedings of the ICASSP, pp. 6469\u20136473 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053407"},{"key":"16_CR4","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1109\/TASLP.2020.2980991","volume":"28","author":"W Cai","year":"2020","unstructured":"Cai, W., Chen, J., Zhang, J., Li, M.: On-the-fly data loader and utterance-level aggregation for speaker and language recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 28, 1038\u20131051 (2020)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"16_CR5","unstructured":"Caro\u00a0Repetto, R., Serra, X.: Creating a corpus of jingju (Beijing opera) music and possibilities for melodic analysis. In: Proceedings of the ISMIR (2014)"},{"issue":"5","key":"16_CR6","doi-asserted-by":"publisher","first-page":"2923","DOI":"10.3390\/su14052923","volume":"14","author":"Q Chen","year":"2022","unstructured":"Chen, Q., Zhao, W., Wang, Q., Zhao, Y.: The sustainable development of intangible cultural heritage with AI: cantonese opera singing genre classification based on cogcnet model in china. Sustainability 14(5), 2923 (2022)","journal-title":"Sustainability"},{"issue":"4","key":"16_CR7","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2010","unstructured":"Dehak, N., Kenny, P.J., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788\u2013798 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of the CVPR, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Desplanques, B., Thienpondt, J., Demuynck, K.: ECAPA-TDNN: emphasized channel attention, propagation and aggregation in tdnn based speaker verification. In: Proceedings of the Interspeech, pp. 3830\u20133834 (2020)","DOI":"10.21437\/Interspeech.2020-2650"},{"issue":"1","key":"16_CR10","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.jvoice.2013.07.012","volume":"28","author":"L Dong","year":"2014","unstructured":"Dong, L., Sundberg, J., Kong, J.: Loudness and pitch of Kunqu opera. J. Voice 28(1), 14\u201319 (2014)","journal-title":"J. Voice"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Fan, Y., et al.: CN-CELEB: a challenging Chinese speaker recognition dataset. In: Proceedings of the ICASSP, pp. 7604\u20137608 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054017"},{"key":"16_CR12","unstructured":"Gong, R., Caro, R., Zhu, T.: Jingju a cappella recordings collection (2019). https:\/\/doi.org\/10.5281\/zenodo.3251761"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Han, B., Chen, Z., Qian, Y.: Local information modeling with self-attention for speaker verification. In: Proceedings of the ICASSP, pp. 6727\u20136731 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746050"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"50","key":"16_CR15","doi-asserted-by":"publisher","first-page":"2154","DOI":"10.21105\/joss.02154","volume":"5","author":"R Hennequin","year":"2020","unstructured":"Hennequin, R., Khlif, A., Voituret, F., Moussallam, M.: Spleeter: a fast and efficient music source separation tool with pre-trained models. J. Open Sour. Softw. 5(50), 2154 (2020)","journal-title":"J. Open Sour. Softw."},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Islam, R., Xu, M., Fan, Y.: Chinese traditional opera database for music genre recognition. In: Proceedings of the O-COCOSDA\/CASLRE, pp. 38\u201341 (2015)","DOI":"10.1109\/ICSDA.2015.7357861"},{"issue":"2","key":"16_CR17","doi-asserted-by":"publisher","first-page":"152","DOI":"10.2307\/834024","volume":"20","author":"H Jinpei","year":"1989","unstructured":"Jinpei, H.: Xipi and erhuang of Beijing and Guangdong operas. Asian Music 20(2), 152\u2013195 (1989)","journal-title":"Asian Music"},{"key":"16_CR18","unstructured":"Kim, J., Kong, J., Son, J.: Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech. In: Proceedings of the ICML, pp. 5530\u20135540 (2021)"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Li, Q., Hu, B.: Joint time and frequency transformer for Chinese opera classification. In: Proceedings of the Interspeech (2023)","DOI":"10.21437\/Interspeech.2023-1582"},{"key":"16_CR20","unstructured":"Lin, L.: Modernising Cantonese opera through contemporary sound production design. Ph.D. thesis, Middlesex University (2022)"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Lin, Y., Cheng, M., Zhang, F., Gao, Y., Zhang, S., Li, M.: VoxBlink2: a 100k+ speaker recognition corpus and the open-set speaker-identification benchmark. arXiv preprint arXiv:2407.11510 (2024)","DOI":"10.21437\/Interspeech.2024-1490"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Lin, Y., Qin, X., Jiang, N., Zhao, G., Li, M.: Haha-pod: an attempt for laughter-based non-verbal speaker verification. In: Proceedings of the ASRU, pp.\u00a01\u20137 (2023)","DOI":"10.1109\/ASRU57964.2023.10389664"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Chung, J., Zisserman, A.: Voxceleb: a large-scale speaker identification dataset. In: Proceedings of the Interspeech (2017)","DOI":"10.21437\/Interspeech.2017-950"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Okabe, K., Koshinaka, T., Shinoda, K.: Attentive statistics pooling for deep speaker embedding. arXiv preprint arXiv:1803.10963 (2018)","DOI":"10.21437\/Interspeech.2018-993"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Peng, Z., Wu, J., Li, Y.: Singing voice conversion between popular music and Chinese opera based on ViTs. In: Proceedings of the DASC\/PiCom\/CBDCom\/CyberSciTech, pp. 0999\u20131003 (2023)","DOI":"10.1109\/DASC\/PiCom\/CBDCom\/Cy59711.2023.10361493"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Prince, S.J., Elder, J.H.: Probabilistic linear discriminant analysis for inferences about identity. In: Proceedings of the ICCV, pp.\u00a01\u20138 (2007)","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"16_CR27","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1109\/TASLP.2022.3212834","volume":"31","author":"X Qin","year":"2022","unstructured":"Qin, X., Cai, D., Li, M.: Robust multi-channel far-field speaker verification under different in-domain data availability scenarios. IEEE\/ACM Trans. Audio Speech Lang. Process. 31, 71\u201385 (2022)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"16_CR28","unstructured":"Qin, X., et al.: The DKU-tencent system for the voxceleb speaker recognition challenge 2022. arXiv preprint arXiv:2210.05092 (2022)"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Qin, X., Li, N., Weng, C., Su, D., Li, M.: Cross-age speaker verification: learning age-invariant speaker embeddings. In: Proceedings of the Interspeech (2022)","DOI":"10.21437\/Interspeech.2022-648"},{"key":"16_CR30","unstructured":"Ren, Y., et al.: FastSpeech 2: fast and high-quality end-to-end text to speech. In: Proceedings of the ICLR (2020)"},{"issue":"1\u20133","key":"16_CR31","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1006\/dspr.1999.0361","volume":"10","author":"DA Reynolds","year":"2000","unstructured":"Reynolds, D.A., Quatieri, T.F., Dunn, R.B.: Speaker verification using adapted gaussian mixture models. Digit. Signal Process. 10(1\u20133), 19\u201341 (2000)","journal-title":"Digit. Signal Process."},{"key":"16_CR32","unstructured":"Serra, X.: Creating research corpora for the computational study of music: the case of the compmusic project. In: Audio Engineering Society Conference: 53rd International Conference: Semantic Audio (2014)"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Povey, D., Khudanpur, S.: Deep neural network embeddings for text-independent speaker verification. In: Proceedings of the Interspeech, vol.\u00a02017, pp. 999\u20131003 (2017)","DOI":"10.21437\/Interspeech.2017-620"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., Khudanpur, S.: X-vectors: robust DNN embeddings for speaker recognition. In: Proceedings of the ICASSP, pp. 5329\u20135333 (2018)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"16_CR35","unstructured":"Srinivasamurthy, A., Caro\u00a0Repetto, R., Sundar, H., Serra, X.: Transcription and recognition of syllable based percussion patterns: the case of Beijing opera. In: Proceedings of the ISMIR, pp. 431\u2013436 (2014)"},{"issue":"7","key":"16_CR36","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1109\/LSP.2018.2822810","volume":"25","author":"F Wang","year":"2018","unstructured":"Wang, F., Cheng, J., Liu, W., Liu, H.: Additive margin softmax for face verification. IEEE Signal Process. Lett. 25(7), 926\u2013930 (2018)","journal-title":"IEEE Signal Process. Lett."},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: WeSpeaker: a research and production oriented speaker embedding learning toolkit. In: Proceedings of the ICASSP, pp.\u00a01\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"key":"16_CR38","doi-asserted-by":"crossref","unstructured":"Wang, S., Yang, Y., Qian, Y., Yu, K.: Revisiting the statistics pooling layer in deep speaker embedding learning. In: Proceedings of the ISCSLP, pp.\u00a01\u20135 (2021)","DOI":"10.1109\/ISCSLP49672.2021.9362097"},{"key":"16_CR39","unstructured":"Wang, W.: Kunqu yishu dadian (\n\n                \n              \n). Anhui Literature and Art Publishing House, Anhui (2016). http:\/\/www.awpub.com\/front\/book\/10-858"},{"key":"16_CR40","unstructured":"Wichmann, E.: Listening to Theatre: The Aural Dimension of Beijing Opera. University of Hawaii Press (1991)"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Wu, Y., et al.: Synthesising expressiveness in Peking opera via duration informed attention network. arXiv preprint arXiv:1912.12010 (2019)","DOI":"10.21437\/Interspeech.2020-1724"},{"key":"16_CR42","doi-asserted-by":"crossref","unstructured":"Wu, Y., et al.: Peking opera synthesis via duration informed attention network. In: Proceedings of the Interspeech (2020)","DOI":"10.21437\/Interspeech.2020-1724"},{"key":"16_CR43","unstructured":"Yang, L., Zhang, R.Y., Li, L., Xie, X.: SimAM: a simple, parameter-free attention module for convolutional neural networks. In: Proceedings of the ICML, pp. 11863\u201311874 (2021)"},{"key":"16_CR44","unstructured":"Yang, L., Tian, M., Chew, E., et\u00a0al.: Vibrato characteristics and frequency histogram envelopes in Beijing opera singing (2015)"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Yao, M., Liu, J.: The analysis of Chinese and Japanese traditional opera tunes with artificial intelligence technology based on deep learning. IEEE Access (2024)","DOI":"10.1109\/ACCESS.2024.3362799"},{"key":"16_CR46","unstructured":"Yu, C., et\u00a0al.: DurIAN: duration informed attention network for multimodal synthesis. arXiv preprint arXiv:1909.01700 (2019)"},{"issue":"3","key":"16_CR47","doi-asserted-by":"publisher","first-page":"439","DOI":"10.2307\/850654","volume":"27","author":"B Yung","year":"1983","unstructured":"Yung, B.: Creative process in cantonese opera iii: the role of padding syllables. Ethnomusicology 27(3), 439\u2013456 (1983)","journal-title":"Ethnomusicology"},{"key":"16_CR48","unstructured":"Zhang, H., Jiang, Y., Zhao, W., Jiang, T., Hu, P., Entertainment, T.M.: Chinese opera genre investigation by convolutional neural network. In: Proceedings of the ISMIR (2021)"},{"key":"16_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, X., Sun, W., Shi, X.: A high-quality melody-aware Peking opera synthesizer using data augmentation. In: Proceedings of the ICME, pp. 1092\u20131097 (2023)","DOI":"10.1109\/ICME55011.2023.00191"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78347-0_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T15:03:07Z","timestamp":1733065387000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78347-0_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031783463","9783031783470"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78347-0_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}