{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T04:30:14Z","timestamp":1742963414190,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031780134"},{"type":"electronic","value":"9783031780141"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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\/978-3-031-78014-1_15","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T12:25:01Z","timestamp":1732191901000},"page":"201-209","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Investigating Data Requirements for\u00a0Hindi Speaker Recognition: A Comparative Study with\u00a0English"],"prefix":"10.1007","author":[{"given":"Parth","family":"Khadse","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sabyasachi","family":"Chandra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Puja","family":"Bharati","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Debolina","family":"Pramanik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"G. Satya","family":"Prasad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aniket","family":"Aitawade","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shyamal Kumar Das","family":"Mandal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A., Zisserman, A.: VoxCeleb2: Deep speaker recognition. arXiv preprint arXiv:1806.05622 (2018)","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"15_CR2","unstructured":"Fang, W., Chung, Y.A., Glass, J.: Towards transfer learning for end-to-end speech synthesis from deep pre-trained language models. arXiv preprint arXiv:1906.07307 (2019)"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Garcia-Romero, D., Snyder, D., Sell, G., McCree, A., Povey, D., Khudanpur, S.: x-vector DNN refinement with full-length recordings for speaker recognition. In: Interspeech, pp. 1493\u20131496 (2019)","DOI":"10.21437\/Interspeech.2019-2205"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Heigold, G., Moreno, I., Bengio, S., Shazeer, N.: End-to-end text-dependent speaker verification. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5115\u20135119. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"15_CR5","unstructured":"Jati, A., Liu, M., McLoughlin, I.V.: Unsupervised transfer learning for speaker recognition. arXiv preprint arXiv:2102.06704 (2021)"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Li, L., Lin, Y., Zhang, Z., Wang, D.: Improved deep speaker feature learning for text-dependent speaker recognition. In: 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), pp. 426\u2013429. IEEE (2015)","DOI":"10.1109\/APSIPA.2015.7415306"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Li, X., Wu, X.: Modeling speaker variability using long short-term memory networks for speech recognition. In: Sixteenth Annual Conference of the International Speech Communication Association (2015)","DOI":"10.21437\/Interspeech.2015-287"},{"key":"15_CR8","unstructured":"Miao, Y., Zhang, L., Chen, S.: Transfer learning for end-to-end speech recognition with transformer. arXiv preprint arXiv:2006.05204 (2020)"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: VoxCeleb: a large-scale speaker identification dataset. arXiv preprint arXiv:1706.08612 (2017)","DOI":"10.21437\/Interspeech.2017-950"},{"key":"15_CR10","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"},{"issue":"10","key":"15_CR11","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2009","unstructured":"Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345\u20131359 (2009)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: LibriSpeech: an ASR corpus based on public domain audio books. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5206\u20135210. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Pascual, S., Park, M., Serr\u00e0, J., Bonafonte, A., Ahn, K.H.: Language and noise transfer in speech enhancement generative adversarial network. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5019\u20135023. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462322"},{"issue":"10","key":"15_CR14","doi-asserted-by":"publisher","first-page":"1671","DOI":"10.1109\/LSP.2015.2420092","volume":"22","author":"F Richardson","year":"2015","unstructured":"Richardson, F., Reynolds, D., Dehak, N.: Deep neural network approaches to speaker and language recognition. IEEE Signal Process. Lett. 22(10), 1671\u20131675 (2015)","journal-title":"IEEE Signal Process. Lett."},{"key":"15_CR15","unstructured":"Sun, L., Henter, G.E., Higuchi, T., Yamamoto, K., Kain, A., Aihara, T.: Transfer learning for voice conversion without parallel data. arXiv preprint arXiv:2106.03198 (2021)"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Variani, E., Lei, X., McDermott, E., Moreno, I.L., Gonzalez-Dominguez, J.: Deep neural networks for small footprint text-dependent speaker verification. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4052\u20134056. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Wan, L., Wang, Q., Papir, A., Moreno, I.L.: Generalized end-to-end loss for speaker verification. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4879\u20134883. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"15_CR18","unstructured":"Wang, Y., Wang, H., Liu, M., Zhang, Y.: Cross-lingual transfer learning for end-to-end speech recognition with transformer. In: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7319\u20137323. IEEE (2020)"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78014-1_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T15:07:17Z","timestamp":1736348837000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78014-1_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031780134","9783031780141"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78014-1_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgrade","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Serbia","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":"25 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom2024.ftn.uns.ac.rs\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}