{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T13:17:42Z","timestamp":1740143862888,"version":"3.37.3"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,2,21]],"date-time":"2019-02-21T00:00:00Z","timestamp":1550707200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Telecommunication Laboratories, Chunghwa Telecom, Taoyuan, Taiwan","award":["No. TL-102-8202"],"award-info":[{"award-number":["No. TL-102-8202"]}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST-106-2221-E-305-010-"],"award-info":[{"award-number":["MOST-106-2221-E-305-010-"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1186\/s13636-019-0147-y","type":"journal-article","created":{"date-parts":[[2019,2,21]],"date-time":"2019-02-21T12:02:40Z","timestamp":1550750560000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Punctuation-generation-inspired linguistic features for Mandarin prosody generation"],"prefix":"10.1186","volume":"2019","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4997-8774","authenticated-orcid":false,"given":"Chen-Yu","family":"Chiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Ping","family":"Hung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han-Yun","family":"Yeh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"I-Bin","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen-Ming","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,2,21]]},"reference":[{"key":"147_CR1","first-page":"13","volume-title":"Proc. Oriental Co-ordination and Standardization of Speech Databases and Assessment Techniques (O-COCOSDA) Workshop, Taipei, Taiwan","author":"AJ Li","year":"1999","unstructured":"Li, A. J., Zu, Y. Q., & Li, Z. Q. (1999). A national database design and prosodic labeling for speech synthesis. In Proc. Oriental Co-ordination and Standardization of Speech Databases and Assessment Techniques (O-COCOSDA) Workshop, Taipei, Taiwan (pp. 13\u201316)."},{"key":"147_CR2","first-page":"13","volume-title":"Proceedings of the International Conference on Spoken Language Processing (ICSLP), Beijing, China","author":"AJ Li","year":"2000","unstructured":"Li, A. J., & Lin, M. C. (2000). Speech corpus of Chinese discourse and the phonetic research. In Proceedings of the International Conference on Spoken Language Processing (ICSLP), Beijing, China (pp. 13\u201318)."},{"key":"147_CR3","first-page":"357","volume-title":"Proceedings of the International Conference on Spoken Language Processing (ICSLP), Beijing, China","author":"JF Cao","year":"2000","unstructured":"Cao, J. F. (2000). Rhythm of spoken Chinese\u2014Linguistic and paralinguistic evidences. In Proceedings of the International Conference on Spoken Language Processing (ICSLP), Beijing, China (pp. 357\u2013360)."},{"key":"147_CR4","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1109\/89.668817","volume":"6","author":"SH Chen","year":"1998","unstructured":"Chen, S. H., Hwang, S. H., & Wang, Y. R. (1998). An RNN-based prosodic information synthesizer for Mandarin text-to-speech. IEEE Trans. Speech Audio Process., 6, 226\u2013239.","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"147_CR5","doi-asserted-by":"publisher","first-page":"908","DOI":"10.1121\/1.1841572","volume":"117","author":"SH Chen","year":"2005","unstructured":"Chen, S. H., Lai, W. H., & Wang, Y. R. (2005). A statistics-based pitch contour model for Mandarin speech. J. Acoust. Soc. Am., 117, 908\u2013925.","journal-title":"J. Acoust. Soc. Am."},{"key":"147_CR6","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1109\/TSA.2003.814377","volume":"11","author":"SH Chen","year":"2003","unstructured":"Chen, S. H., Lai, W. H., & Wang, Y. R. (2003). A new duration modeling approach for Mandarin speech. IEEE Trans. Speech Audio Process., 11, 308\u2013320.","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"147_CR7","first-page":"1315","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Istanbul, Turkey","author":"K Tokuda","year":"2000","unstructured":"Tokuda, K., Yoshimur, T., Masuko, T., Kobayashi, T., & Kitamura, T. (2000). Speech parameter generation algorithms for HMM-based speech synthesis. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Istanbul, Turkey (pp. 1315\u20131318)."},{"key":"147_CR8","volume-title":"Simultaneous modeling of phonetic and prosodic parameters, and characteristic conversion for HMM-based text-to-speech systems","author":"T Yoshimura","year":"2002","unstructured":"Yoshimura, T. (2002). Simultaneous modeling of phonetic and prosodic parameters, and characteristic conversion for HMM-based text-to-speech systems. Nagoya: Dissertation, Nagoya Institute of Technology."},{"key":"147_CR9","first-page":"294","volume-title":"Proceedings of the Sixth ISCA Workshop on Speech Synthesis (SSW6), Bonn, Germany","author":"H Zen","year":"2007","unstructured":"Zen, H., Nose, T., Yamagishi, J., Sako, S., Masuko, T., Black, A. W., & Tokuda, K. (2007). The HMM-based speech synthesis system version 2.0. In Proceedings of the Sixth ISCA Workshop on Speech Synthesis (SSW6), Bonn, Germany (pp. 294\u2013299)."},{"key":"147_CR10","unstructured":"The HTS working group, HTS-2.3 source code, and demonstrations. http:\/\/hts.sp.nitech.ac.jp\/?Download . Accessed 26 Jan 2018."},{"key":"147_CR11","first-page":"27","volume":"20","author":"M Ostendorf","year":"1994","unstructured":"Ostendorf, M., & Veilleux, N. (1994). A hierarchical stochastic model for automatic prediction of prosodic boundary location. Comput. Linguist., 20, 27\u201352.","journal-title":"Comput. Linguist."},{"key":"147_CR12","first-page":"173","volume-title":"Proceedings of the International Symposium on Chinese Spoken Language Processing (ISCSLP), Hong Kong","author":"HJ Peng","year":"2004","unstructured":"Peng, H. J., Chen, C. C., Tseng, C. Y., & Chen, K. J. (2004). Predicting prosodic words from lexical words\u2014a first step towards predicting prosody from text. In Proceedings of the International Symposium on Chinese Spoken Language Processing (ISCSLP), Hong Kong (pp. 173\u2013176)."},{"key":"147_CR13","first-page":"61","volume":"6","author":"M Chu","year":"2001","unstructured":"Chu, M., & Qian, Y. (2001). Locating boundaries for prosodic constituents in unrestricted mandarin texts. Comput. Linguist. Chin. Lang. Process., 6, 61\u201382.","journal-title":"Comput. Linguist. Chin. Lang. Process."},{"key":"147_CR14","first-page":"14","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toulouse, France","author":"DW Xu","year":"2006","unstructured":"Xu, D. W., Wang, H. F., Li, G. H., & Kagoshima, T. (2006). Parsing hierarchical prosodic structure for Mandarin speech synthesis. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toulouse, France (pp. 14\u201319)."},{"key":"147_CR15","doi-asserted-by":"crossref","first-page":"995","DOI":"10.21437\/Eurospeech.1997-351","volume-title":"Proceedings of the European Conference on Speech Communication and Technology (Eurospeech), Rhodes, Greece","author":"AW Black","year":"1997","unstructured":"Black, A. W., & Taylor, P. (1997). Assigning phrase breaks from part-of-speech sequences. In Proceedings of the European Conference on Speech Communication and Technology (Eurospeech), Rhodes, Greece (pp. 995\u2013998)."},{"key":"147_CR16","first-page":"492","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hong Kong","author":"Z Sheng","year":"2003","unstructured":"Sheng, Z., Tao, J. H., & Jiang, D. L. (2003). Chinese prosodic phrasing with extended features. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hong Kong (pp. 492\u2013495)."},{"key":"147_CR17","first-page":"729","volume-title":"Proceedings of the International Conference on Spoken Language Processing (ICSLP), Jeju Island, Korea","author":"JF Li","year":"2004","unstructured":"Li, J. F., Hu, G. P., & Wang, R. H. (2004). Chinese prosody phrase break prediction based on maximum entropy model. In Proceedings of the International Conference on Spoken Language Processing (ICSLP), Jeju Island, Korea (pp. 729\u2013732)."},{"key":"147_CR18","doi-asserted-by":"crossref","first-page":"599","DOI":"10.21437\/Eurospeech.1995-152","volume-title":"Proceedings of the European Conference on Speech Communication and Technology (Eurospeech), Madrid, Spain","author":"M Riedi","year":"1995","unstructured":"Riedi, M. (1995). A neural-network-based model of segmental duration for speech synthesis. In Proceedings of the European Conference on Speech Communication and Technology (Eurospeech), Madrid, Spain (pp. 599\u2013602)."},{"key":"147_CR19","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1109\/ICASSP.1990.115662","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Albuquerque, New Mexico, USA","author":"Y Sagisaka","year":"1990","unstructured":"Sagisaka, Y. (1990). On the prediction of global F0 shape for Japanese text-to-speech. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Albuquerque, New Mexico, USA (pp. 325\u2013328)."},{"key":"147_CR20","volume-title":"Talking Machines: Theories, Models and Designs","author":"C Traber","year":"1992","unstructured":"Traber, C. (1992). In G. Bailly & C. Benoit (Eds.), Talking Machines: Theories, Models and Designs. Amsterdam: Elsevier."},{"key":"147_CR21","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1109\/ICASSP.1989.266404","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Glasgow, Scotland","author":"MS Scordilis","year":"1989","unstructured":"Scordilis, M. S., & Gowdy, J. N. (1989). Neural network based generation of fundamental frequency contours. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Glasgow, Scotland (pp. 219\u2013222)."},{"key":"147_CR22","first-page":"117","volume-title":"Proceedings of the International Symposium on Chinese Spoken Language Processing (ISCSLP), Hong Kong","author":"GB GP Chen","year":"2004","unstructured":"GP Chen, G. B., Liu, Q. F., & Wang, R. H. (2004). A superposed prosodic model for Chinese text-to-speech synthesis. In Proceedings of the International Symposium on Chinese Spoken Language Processing (ISCSLP), Hong Kong (pp. 117\u2013120)."},{"key":"147_CR23","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1016\/j.specom.2005.04.008","volume":"46","author":"G Bailly","year":"2006","unstructured":"Bailly, G., & Holm, B. (2006). SFC: a trainable prosodic model. Speech Comm., 46, 348\u2013364.","journal-title":"Speech Comm."},{"key":"147_CR24","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1109\/ICOSP.2010.5656843","volume-title":"Proceedings of the 10th IEEE International Conference on Signal Processing (ICSP), Beijing, China","author":"MM Wen","year":"2010","unstructured":"Wen, M. M., Wang, M. M., Hirose, K., & Minematsu, N. (2010). Improved Mandarin segmental duration prediction with automatically extracted syntax features. In Proceedings of the 10th IEEE International Conference on Signal Processing (ICSP), Beijing, China (pp. 621\u2013624)."},{"issue":"8","key":"147_CR25","doi-asserted-by":"publisher","first-page":"1994","DOI":"10.1109\/TASL.2010.2040791","volume":"18","author":"CHW CC Hsia","year":"2010","unstructured":"CC Hsia, C. H. W., & Wu, J. Y. (2010). Exploiting prosody hierarchy and dynamic features for pitch modeling and generation in HMM-based speech synthesis. IEEE Trans. Audio Speech Lang. Process., 18(8), 1994\u20132003.","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"147_CR26","first-page":"359","volume-title":"Proceedings of the Seventh ISCA Workshop on Speech Synthesis (SSW7), Kyoto, Japan","author":"MM Wang","year":"2010","unstructured":"Wang, M. M., Wen, M. M., Hirose, K., & Minematsu, N. (2010). Improved Generation of Prosodic Features in HMM-based Speech Synthesis. In Proceedings of the Seventh ISCA Workshop on Speech Synthesis (SSW7), Kyoto, Japan (pp. 359\u2013336)."},{"key":"147_CR27","first-page":"2166","volume-title":"Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH), Makuhari, Chiba, Japan","author":"MM Wang","year":"2010","unstructured":"Wang, M. M., Wen, M. M., Hirose, K., & Minematsu, N. (2010). Improved generation of fundamental frequency in HMM-based speech synthesis using generation process model. In Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH), Makuhari, Chiba, Japan (pp. 2166\u20132169)."},{"key":"147_CR28","first-page":"4597","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan","author":"CY Chiang","year":"2012","unstructured":"Chiang, C. Y., Wang, Y. R., & Chen, S. H. (2012). Punctuation generation inspired linguistic features for Mandarin prosodic boundary prediction. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan (pp. 4597\u20134600)."},{"key":"147_CR29","first-page":"1","volume-title":"Proceedings of the 17th Oriental Chapter of the International Committee for the Co-ordination and Standardization of Speech Databases and Assessment Techniques (O-COCOSDA), Phuket, Thailand","author":"YP Hung","year":"2014","unstructured":"Hung, Y. P., Yeh, H. Y., Liao, I. B., Pan, C. M., & Chiang, C. Y. (2014). An investigation on linguistic features for Mandarin prosody generation. In Proceedings of the 17th Oriental Chapter of the International Committee for the Co-ordination and Standardization of Speech Databases and Assessment Techniques (O-COCOSDA), Phuket, Thailand (pp. 1\u20135)."},{"key":"147_CR30","first-page":"1","volume-title":"Proceedings of the 10th International Symposium on Chinese Spoken Language Processing (ISCSLP), Tianjin, China","author":"CY Chiang","year":"2016","unstructured":"Chiang, C. Y., Hung, Y. P., Liou, G. T., & Wang, Y. R. (2016). Improvements on punctuation generation inspired linguistic features for Mandarin prosody generation. In Proceedings of the 10 th International Symposium on Chinese Spoken Language Processing (ISCSLP), Tianjin, China (pp. 1\u20135)."},{"key":"147_CR31","volume-title":"Punctuation Generation Inspired Linguistic Features for Mandarin Prosody Generation","author":"YP Hung","year":"2015","unstructured":"Hung, Y. P. (2015). Punctuation Generation Inspired Linguistic Features for Mandarin Prosody Generation. New Taipei City: Master, National Taipei University."},{"issue":"2","key":"147_CR32","first-page":"6","volume":"9","author":"HF YQ Guo","year":"2010","unstructured":"YQ Guo, H. F., Wang, J. V., & Genabith, A. (2010). Linguistically inspired statistical model for Chinese punctuation generation. ACM Trans. Asian Lang. Process., 9(2), 6.","journal-title":"ACM Trans. Asian Lang. Process."},{"key":"147_CR33","doi-asserted-by":"crossref","first-page":"2341","DOI":"10.21437\/Eurospeech.2003-646","volume-title":"Proceedings of the European Conference on Speech Communication and Technology (Eurospeech), Geneva, Switzerland","author":"CY Tseng","year":"2003","unstructured":"Tseng, C. Y. (2003). Mandarin speech prosody: issues, pitfalls and directions. In Proceedings of the European Conference on Speech Communication and Technology (Eurospeech), Geneva, Switzerland (pp. 2341\u20132344)."},{"key":"147_CR34","unstructured":"http:\/\/www.aclclp.org.tw\/use_asbc.php . Accessed 15 Mar 2018."},{"key":"147_CR35","first-page":"282","volume-title":"Proceedings of the Eighteenth International Conference on Machine Learning (ICML 2001), Williamstown, MA, USA","author":"J Lafferty","year":"2001","unstructured":"Lafferty, J., McCallum, A., & Pereira, F. (2001). Conditional random fields: probabilistic models for segmenting and labeling sequence data. In Proceedings of the Eighteenth International Conference on Machine Learning (ICML 2001), Williamstown, MA, USA (pp. 282\u2013289)."},{"key":"147_CR36","unstructured":"CRF++: Yet Another CRF toolkit. https:\/\/taku910.github.io\/crfpp\/ . Accessed on 26 Jan 2018."},{"key":"147_CR37","first-page":"867","volume-title":"Proceedings of the International Conference on Spoken Language Processing (ICSLP), Banff, Alberta, Canada","author":"K Silverman","year":"1992","unstructured":"Silverman, K., Beckman, M., Pitrelli, J., Ostendorf, M., Wightman, C., Price, P., Pierrehumbert, J., & Hirschberg, J. (1992). ToBI: a standard for labeling English prosody. In Proceedings of the International Conference on Spoken Language Processing (ICSLP), Banff, Alberta, Canada (pp. 867\u2013870)."},{"key":"147_CR38","first-page":"1383","volume-title":"Proceedings of the International Conference on Spoken Language Processing (ICSLP), Sydney, Australia","author":"PA Taylor","year":"1998","unstructured":"Taylor, P. A. (1998). The tilt intonation model. In Proceedings of the International Conference on Spoken Language Processing (ICSLP), Sydney, Australia (pp. 1383\u20131386)."},{"key":"147_CR39","first-page":"39","volume-title":"Proceedings of the ISCA International Conference on Speech Prosody (Speech Prosody), Aix-en-Provence, France","author":"AJ Li","year":"2002","unstructured":"Li, A. J. (2002). Chinese prosody and prosodic labeling of spontaneous speech. In Proceedings of the ISCA International Conference on Speech Prosody (Speech Prosody), Aix-en-Provence, France (pp. 39\u201346)."},{"issue":"2","key":"147_CR40","doi-asserted-by":"publisher","first-page":"1164","DOI":"10.1121\/1.3056559","volume":"125","author":"CY Chiang","year":"2009","unstructured":"Chiang, C. Y., Chen, S. H., Yu, H. M., & Wang, Y. R. (2009). Unsupervised joint prosody labeling and modeling for Mandarin speech. J. Acoust. Soc. Amer., 125(2), 1164\u20131183.","journal-title":"J. Acoust. Soc. Amer."},{"key":"147_CR41","first-page":"504","volume-title":"Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH), Brighton, UK","author":"CY Chiang","year":"2009","unstructured":"Chiang, C. Y., Chen, S. H., & Wang, Y. R. (2009). Advanced unsupervised joint prosody labeling and modeling for Mandarin speech and its application to prosody generation for TTS. In Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH), Brighton, UK (pp. 504\u2013507)."},{"issue":"6","key":"147_CR42","doi-asserted-by":"publisher","first-page":"1669","DOI":"10.1109\/TASL.2012.2187192","volume":"20","author":"JH SH Chen","year":"2012","unstructured":"SH Chen, J. H., Yang, C. Y., Chiang, M. C., Liu, Y. R., & Wang, A. (2012). New prosody-assisted mandarin ASR system. IEEE Trans. Audio Speech Lang. Process., 20(6), 1669\u20131684.","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"147_CR43","unstructured":"The NCTU Speech Lab Traditional Chinese Parser. http:\/\/parser.speech.cm.nctu.edu.tw\/ Accessed on 26 Jan 2018."},{"key":"147_CR44","unstructured":"Lin, A. H., Wang, Y. R., & Chen, S. H. (2013). In\u00a0Proceedings of the 17th Oriental Chapter of the International Committee for the Co-ordination and Standardization of Speech Databases and Assessment Techniques (O-COCOSDA), Gurgaon, India (pp. 1\u20135)."},{"key":"147_CR45","unstructured":"Chen, K. J., & Huang, C. R. (1993). Part of speech (POS) analysis on Chinese language. In\u00a0CKIP Technical Report No.93\u201305; Institute of Information Science, Academia Sinica: Taiwan, R.O.C."},{"key":"147_CR46","doi-asserted-by":"crossref","unstructured":"Chiang, C. Y., Yu, H. M., Wang, Y. R., & Chen, S. H. (2008). Exploration of high-level prosodic patterns for continuous Mandarin speech. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Las Vegas, USA\u00a0(pp. 4381\u20134384).","DOI":"10.1109\/ICASSP.2008.4518525"},{"issue":"9","key":"147_CR47","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.1109\/26.61370","volume":"38","author":"SH Chen","year":"1990","unstructured":"Chen, S. H., & Wang, Y. R. (1990). Vector quantization of pitch information in Mandarin speech. IEEE Trans. Commun., 38(9), 1317\u20131320.","journal-title":"IEEE Trans. Commun."},{"key":"147_CR48","first-page":"5","volume-title":"Proceedings of the Workshop on Spoken Language Processing, Mumbai, India","author":"H Fujisaki","year":"2003","unstructured":"Fujisaki, H. (2003). Prosody, information, and modeling: with emphasis on tonal features of speech. In Proceedings of the Workshop on Spoken Language Processing, Mumbai, India (pp. 5\u201314)."},{"issue":"8","key":"147_CR49","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Comput., 9(8), 1735\u20131780.","journal-title":"Neural Comput."},{"key":"147_CR50","first-page":"17","volume-title":"Proceedings of the ICML Workshop on Unsupervised and Transfer Learning, Bellevue, Washington, USA","author":"Y Bengio","year":"2012","unstructured":"Bengio, Y. (2012). Deep learning of representations for unsupervised and transfer learning. In Proceedings of the ICML Workshop on Unsupervised and Transfer Learning, Bellevue, Washington, USA (pp. 17\u201336)."}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-019-0147-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13636-019-0147-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-019-0147-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T08:22:14Z","timestamp":1662970934000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13636-019-0147-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,21]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["147"],"URL":"https:\/\/doi.org\/10.1186\/s13636-019-0147-y","relation":{},"ISSN":["1687-4722"],"issn-type":[{"type":"electronic","value":"1687-4722"}],"subject":[],"published":{"date-parts":[[2019,2,21]]},"assertion":[{"value":"28 March 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 February 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 February 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Publisher\u2019s Note"}}],"article-number":"4"}}