{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T16:29:17Z","timestamp":1747153757765,"version":"3.40.5"},"reference-count":78,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2019,11,28]],"date-time":"2019-11-28T00:00:00Z","timestamp":1574899200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,11,28]],"date-time":"2019-11-28T00:00:00Z","timestamp":1574899200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["106-3011-F-027-006"],"award-info":[{"award-number":["106-3011-F-027-006"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["107-3011-F-027-003"],"award-info":[{"award-number":["107-3011-F-027-003"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["106-2221-E-027-128"],"award-info":[{"award-number":["106-2221-E-027-128"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["107-2221-E-027-102"],"award-info":[{"award-number":["107-2221-E-027-102"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["108-2221-E-027-067"],"award-info":[{"award-number":["108-2221-E-027-067"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["107-2911-I-027-501"],"award-info":[{"award-number":["107-2911-I-027-501"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["108-2911-I-027-501"],"award-info":[{"award-number":["108-2911-I-027-501"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005357","name":"Agent\u00fara na Podporu V\u00fdskumu a V\u00fdvoja","doi-asserted-by":"publisher","award":["SK-TW-2017-0005"],"award-info":[{"award-number":["SK-TW-2017-0005"]}],"id":[{"id":"10.13039\/501100005357","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006108","name":"Kult\u00farna a Edukacn\u00e1 Grantov\u00e1 Agent\u00fara M\u0160VVa\u0160 SR","doi-asserted-by":"publisher","award":["009TUKE-4\/2019"],"award-info":[{"award-number":["009TUKE-4\/2019"]}],"id":[{"id":"10.13039\/501100006108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006109","name":"Vedeck\u00e1 Grantov\u00e1 Agent\u00fara M\u0160VVa\u0160 SR a SAV","doi-asserted-by":"publisher","award":["VEGA-1\/0511\/17"],"award-info":[{"award-number":["VEGA-1\/0511\/17"]}],"id":[{"id":"10.13039\/501100006109","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1007\/s11265-019-01483-4","type":"journal-article","created":{"date-parts":[[2019,11,28]],"date-time":"2019-11-28T07:02:41Z","timestamp":1574924561000},"page":"853-873","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Formosa Speech in the Wild Corpus for Improving Taiwanese Mandarin Speech-Enabled Human-Computer Interaction"],"prefix":"10.1007","volume":"92","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0191-2178","authenticated-orcid":false,"given":"Yuan-Fu","family":"Liao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yung-Hsiang Shawn","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Chen","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu-Hua","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4380-0801","authenticated-orcid":false,"given":"Matus","family":"Pleva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1596-9258","authenticated-orcid":false,"given":"Jozef","family":"Juhar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,11,28]]},"reference":[{"key":"1483_CR1","unstructured":"Boersma, P., & Weenink, D. (2018). Praat: doing phonetics by computer. http:\/\/www.fon.hum.uva.nl\/praat\/. Accessed: 2019-01-28."},{"key":"1483_CR2","doi-asserted-by":"publisher","unstructured":"Bu, H., Du, J., Na, X., Wu, B., Zheng, H. (2018). AISHELL-1: an open-source Mandarin speech corpus and a speech recognition baseline. In 2017 20th Conference of the oriental chapter of international committee for coordination and standardization of speech databases and assessment techniques, O-COCOSDA 2017 (pp. 1\u20135), DOI https:\/\/doi.org\/10.1109\/ICSDA.2017.8384449.","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"1483_CR3","doi-asserted-by":"publisher","unstructured":"Chan, W., Jaitly, N., Le, Q., Vinyals, O. (2016). Listen, attend and spell: a neural network for large vocabulary conversational speech recognition. In ICASSP, IEEE International conference on acoustics, speech and signal processing - proceedings (pp. 4960\u20134964), DOI https:\/\/doi.org\/10.1109\/ICASSP.2016.7472621.","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"1483_CR4","unstructured":"Chang, H.j., Chao, W.c., Lo, T.h., Chen, B. (2018). NTNU Speech recognition system at FSR 2018. In Formosa speech recognition challenge workshop. https:\/\/drive.google.com\/file\/d\/1W2T76fyUj4mSFcKa7Z2kieVZMmdYVoWf. Accessed 2019-01-20."},{"key":"1483_CR5","doi-asserted-by":"publisher","unstructured":"Chang, Y.H.S., Liao, Y.F., Wang, S.M., Wang, J.H., Wang, S.Y., Chen, J.W., Chen, Y.D. (2017). Development of a large-scale Mandarin radio speech corpus. In 2017 IEEE International conference on consumer electronics - Taiwan, ICCE-TW 2017 (pp. 359\u2013360), DOI https:\/\/doi.org\/10.1109\/ICCE-China.2017.7991144.","DOI":"10.1109\/ICCE-China.2017.7991144"},{"key":"1483_CR6","unstructured":"Chen, L.h., Hu, C.k., Hung, L.j., Lin, C.w. (2018). Towards a robust Taiwanese Mandarin automatic speech recognition system with Kaldi toolkit. In Formosa speech recognition challenge workshop. https:\/\/drive.google.com\/file\/d\/15p5T43Qb3XVGkQbPTlH1MlhpdUa-Z-nL. Accessed 2019-01-20."},{"key":"1483_CR7","doi-asserted-by":"publisher","unstructured":"Chiu, C.C., Sainath, T.N., Wu, Y., Prabhavalkar, R., Nguyen, P., Chen, Z., Kannan, A., Weiss, R.J., Rao, K., Gonina, E., Jaitly, N., Li, B., Chorowski, J., Bacchiani, M. (2018). State-of-the-art speech recognition with sequence-to-sequence models. In ICASSP, IEEE International conference on acoustics, speech and signal processing - proceedings (pp. 4774\u20134778), DOI https:\/\/doi.org\/10.1109\/ICASSP.2018.8462105.","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"1483_CR8","unstructured":"Du, J., Na, X., Liu, X., Bu, H. (2018). AISHELL-2: transforming Mandarin ASR research into industrial scale. arXiv:1808.10583. Accessed 2019-01-20."},{"key":"1483_CR9","unstructured":"ELRA Catalogue. (2006). Taiwan Mandarin speecon database \u2013 ELRA catalogue. http:\/\/catalogue.elra.info\/en-us\/repository\/browse\/ELRA-S0212\/. Accessed 2019-01-18."},{"key":"1483_CR10","unstructured":"ESPnet. (2018). ESPnet: end-to-end speech processing toolkit. https:\/\/github.com\/espnet\/espnet. Accessed 2019-01-26."},{"key":"1483_CR11","unstructured":"Facebook Research. (2018). GitHub - facebookresearch\/wav2letter: Facebook AI research automatic speech recognition toolkit. https:\/\/github.com\/facebookresearch\/wav2letter. Accessed 2019-01-28."},{"key":"1483_CR12","doi-asserted-by":"crossref","unstructured":"Ghahremani, P., BabaAli, B., Povey, D., Riedhammer, K., Trmal, J., Khudanpur, S. (2014). A pitch extraction algorithm tuned for automatic speech recognition. In 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP).","DOI":"10.1109\/ICASSP.2014.6854049"},{"key":"1483_CR13","unstructured":"Ghahremani, P., Manohar, V., Hadian, H., Povey, D., Khudanpur, S. (2017). Investigation of transfer learning for ASR using LF-MMI trained neural networks. In ASRU 2017. http:\/\/www.danielpovey.com\/files\/2017_asru_transfer_learning.pdf. Accessed 2019-01-26."},{"key":"1483_CR14","unstructured":"Google. (2018). Cloud speech-to-text. https:\/\/cloud.google.com\/speech-to-text\/. Accessed 2019-01-26."},{"key":"1483_CR15","unstructured":"Hannun, A., Case, C., Casper, J., Catanzaro, B., Diamos, G., Elsen, E., Prenger, R., Satheesh, S., Sengupta, S., Coates, A., Ng, A.Y. (2014). Deep speech: scaling up end-to-end speech recognition. arXiv:http:\/\/arXiv.org\/abs\/1412.5567v2."},{"key":"1483_CR16","unstructured":"Hori, T., Cho, J., Watanabe, S. (2018). End-to-end speech recognition with word-based RNN language models. arXiv:1808.02608."},{"key":"1483_CR17","unstructured":"Hsu, W.H. (2018). A preliminary study on speaker diarization for automatic transcription of broadcast radio speech. Ph.D. thesis, National Taipei university of Technology. https:\/\/ir.lib.ntut.edu.tw\/wSite\/ct?mp=ntut&xItem=71271&ctNode=447. Accessed 2019-01-13."},{"key":"1483_CR18","unstructured":"Huang, C., & Chen, K. (1998). Academia Sinica balanced corpus of Modern Chinese. http:\/\/ckip.iis.sinica.edu.tw\/CKIP\/engversion\/20corpus.htm. Accessed 2019-01-27."},{"key":"1483_CR19","unstructured":"Huang, C.R. (2009). Tagged Chinese gigaword version 2.0. http:\/\/www.ldc.upenn.edu\/Catalog\/catalogEntry.jsp?catalogId=LDC2009T14. Accessed 2019-01-26."},{"key":"1483_CR20","unstructured":"Hung, H.t. (2018). The AlexHT system for FSR challenge. In Formosa speech recognition challenge workshop. https:\/\/drive.google.com\/file\/d\/15hjrTipVW0QOxb_tp_UAV9C2evdORdLu. Accessed 2019-01-20."},{"key":"1483_CR21","unstructured":"IFlyTek. (2018). iFLYTEK open platform \u2014\u2014 China\u2019s first artificial intelligence open platform for mobile internet and intelligent hardware developers. http:\/\/global.xfyun.cn\/. Accessed 2019-01-19."},{"key":"1483_CR22","unstructured":"ISCSLP. (2018). ISCSLP2018 - the 11th international symposium on chinese spoken language processing (ISCSLP 2018). http:\/\/iscslp2018.org\/. Accessed 2019-01-26."},{"key":"1483_CR23","unstructured":"Jaitly, N., & Hinton, G.E. (2013). Vocal tract length perturbation (VTLP) improves speech recognition. In ICML Workshop on deep learning for audio, speech and language. https:\/\/pdfs.semanticscholar.org\/3de0\/616eb3cd4554fdf9fd65c9c82f2605a17413.pdf. Accessed 2019-01-26."},{"key":"1483_CR24","unstructured":"Kaldi-ASR. (2018). Kaldi speech recognition toolkit. https:\/\/github.com\/kaldi-asr\/kaldi. Accessed 2019-01-27."},{"key":"1483_CR25","doi-asserted-by":"crossref","unstructured":"Kanda, N., Fujita, Y., Nagamatsu, K. (2018). Lattice-free state-level minimum Bayes risk training of acoustic models.","DOI":"10.21437\/Interspeech.2018-79"},{"key":"1483_CR26","unstructured":"KingLine Data Center. (2018). KingLine data center. http:\/\/kingline.speechocean.com\/. Accessed 2019-01-26."},{"key":"1483_CR27","unstructured":"KingLine Data Center. (2018). Taiwanese and english mixed speech recognition corpus (Mobile)-Sentences-1026 Speakers_ASR-Corpus_Commercial Resources_KingLine Data Center. http:\/\/kingline.speechocean.com\/exchange.php?id=14927&act=view. Accessed 2019-01-27."},{"key":"1483_CR28","unstructured":"KingLine Data Center. (2018). Taiwanese speech recognition corpus (desktop)-conversation-300 Speakers_ASR-Corpus_ Commercial Resources_KingLine Data Center. http:\/\/kingline.speechocean.com\/exchange.php?id=19262&act=view. Accessed 2019-01-27."},{"key":"1483_CR29","unstructured":"KingLine Data Center. (2018). Taiwanese speech recognition corpus (desktop)-sentences-204 Speakers_ASR-Corpus_Commercial Resources_KingLine Data Center. http:\/\/kingline.speechocean.com\/exchange.php?act=view&id=1548. Accessed 2019-01-27."},{"key":"1483_CR30","unstructured":"KingLine Data Center. (2018). Taiwanese speech recognition corpus (mobile)-conversation-300 Speakers_ASR-Corpus_ Commercial Resources_KingLine Data Center. http:\/\/kingline.speechocean.com\/exchange.php?id=19228&act=view. Accessed 2019-01-27."},{"key":"1483_CR31","unstructured":"KingLine Data Center. (2018). Taiwanese speech recognition corpus (mobile)-Ssentences-5232 Speakers_ASR-Corpus_ Commercial Resources_KingLine Data Center. http:\/\/kingline.speechocean.com\/exchange.php?id=766&act=view. Accessed 2019-01-27."},{"key":"1483_CR32","unstructured":"Ko, T., Peddinti, V., Povey, D., Khudanpur, S. (2015). Audio augmentation for speech recognition. In Proceedings of the annual conference of the international speech communication association, INTERSPEECH. https:\/\/www.danielpovey.com\/files\/2015_interspeech_augmentation.pdf. Accessed 2019-01-26 (pp. 3586\u20133589)."},{"key":"1483_CR33","unstructured":"Lee, H.s., Chen, K.y., Tsao, Y., Wang, H.m. (2018). The AS Kaldi-based Taiwanese Mandarin ASR system for FSR-2018. In Formosa speech recognition challenge workshop. https:\/\/drive.google.com\/file\/d\/15gsMr_ZtT6Wuotz8-T9Gysj-7-tJz4Mw. Accessed 2019-01-20."},{"key":"1483_CR34","unstructured":"Liang, H.b., & Wang, Y.r. (2018). The NCTU ASR system for Formosa speech recognition challenge 2018. In Formosa speech recognition challenge workshop. https:\/\/drive.google.com\/file\/d\/15inv3RHf9bTxwhwqrXwWbqNcxAfDgoxl. Accessed 2019-01-20."},{"key":"1483_CR35","unstructured":"Liao, Y.F. (2018). Call for FSR-2018 participants - ISCSLP2018. http:\/\/iscslp2018.org\/CFParticipants.html. Accessed 2019-01-26."},{"key":"1483_CR36","unstructured":"Liao, Y.F. (2018). Formosa speech in the wild corpus. https:\/\/sites.google.com\/speech.ntut.edu.tw\/fsw\/home\/corpus. Accessed 2019-01-26."},{"key":"1483_CR37","unstructured":"Liao, Y.F. (2018). Formosa speech in the wild project - GitLab server. https:\/\/speech.nchc.org.tw. Accessed 2019-01-27."},{"key":"1483_CR38","unstructured":"Liao, Y.F. (2018). Formosa speech recognition challenge 2018. https:\/\/sites.google.com\/speech.ntut.edu.tw\/fsw\/home\/challenge. Accessed 2019-01-26."},{"key":"1483_CR39","unstructured":"Liao, Y.F. (2018). Formosa speech recognition challenge 2018. https:\/\/sites.google.com\/speech.ntut.edu.tw\/fsw\/home\/workshop. Accessed 2019-01-26."},{"key":"1483_CR40","unstructured":"Liao, Y.F. (2018). Formosa speech recognition recipe. https:\/\/github.com\/yfliao\/kaldi\/tree\/master\/egs\/formosa. Accessed 2019-01-28."},{"key":"1483_CR41","unstructured":"Liao, Y.F. (2018). Formosa speech recognition recipe. https:\/\/github.com\/kaldi-asr\/kaldi\/tree\/master\/egs\/formosa. Accessed 2019-01-28."},{"key":"1483_CR42","unstructured":"Liao, Y.F. (2018). Kaldi pull request #2474-formosa_speech recipe and database for Taiwanese Mandarin speech recognition. https:\/\/github.com\/kaldi-asr\/kaldi\/pull\/2474. Accessed 2019-01-28."},{"key":"1483_CR43","doi-asserted-by":"publisher","unstructured":"Liao, Y.F., Chang, Y.H.S., Wang, S.Y., Chen, J.W., Wang, S.M., Wang, J.H. (2018). A progress report of the Taiwan Mandarin radio speech corpus project. In 2017 20th conference of the oriental chapter of international committee for coordination and standardization of speech databases and assessment techniques, O-COCOSDA 2017 (pp. 1\u20136), DOI https:\/\/doi.org\/10.1109\/ICSDA.2017.8384450.","DOI":"10.1109\/ICSDA.2017.8384450"},{"key":"1483_CR44","doi-asserted-by":"crossref","unstructured":"Liao, Y.F., Hsu, W.H., Lin, Y.C., Chang, Y.h.S., Pleva, M. (2018). Formosa speech recognition challenge 2018: data, plan and baselines, IEEE.","DOI":"10.1109\/ISCSLP.2018.8706700"},{"key":"1483_CR45","unstructured":"Linguistic Data Consortium. (1996). CALLFRIEND Mandarin Chinese-Taiwan dialect - linguistic data consortium. https:\/\/catalog.ldc.upenn.edu\/LDC96S56. Accessed 2019-01-27."},{"key":"1483_CR46","unstructured":"Linguistic Data Consortium. (1998). Taiwanese Putonghua speech and transcripts - linguistic data consortium. https:\/\/catalog.ldc.upenn.edu\/LDC98S72. Accessed 2019-01-27."},{"key":"1483_CR47","unstructured":"Linguistic Data Consortium. (2008). U.o.P.: linguistic data consortium webpage. https:\/\/www.ldc.upenn.edu\/. Accessed 2019-01-26."},{"key":"1483_CR48","unstructured":"Lu, M.p., & Chen, C.p. (2018). NSYSU team for the Formosa speech recognition challenge 2018. In Formosa speech recognition challenge workshop. https:\/\/drive.google.com\/file\/d\/15ndD-mwfM3JZ0DX_6BfArxSdb5J1dDYQ. Accessed 2019-01-20."},{"key":"1483_CR49","unstructured":"Lu, M.p., & Chen, C.p. (2018). NSYSU team for the Formosa speech recognition challenge 2018. In: Formosa speech recognition challenge workshop. https:\/\/drive.google.com\/file\/d\/15ndD-mwfM3JZ0DX_6BfArxSdb5J1dDYQ. Accessed 2019-01-20."},{"key":"1483_CR50","doi-asserted-by":"crossref","unstructured":"Manohar, V., Hadian, H., Povey, D., Khudanpur, S. (2018). Semi-supervised training of acoustic models using lattice-free MMI. In ICASSP 2018 (pp. 4844\u20134848).","DOI":"10.1109\/ICASSP.2018.8462331"},{"key":"1483_CR51","unstructured":"Mikolov, T., Kombrink, S., Deoras, A., Burget, L., \u010cernock\u00fd, J. (2011). RNNLM - recurrent neural network language modeling toolkit. In Proceedings of ASRU 2011. http:\/\/www.fit.vutbr.cz\/imikolov\/rnnlm\/rnnlm-demo.pdf. Accessed 2019-01-20 (pp. 196\u2013201)."},{"issue":"2","key":"1483_CR52","doi-asserted-by":"publisher","first-page":"449","DOI":"10.4149\/cai_2017_2_449","volume":"36","author":"Z Milivojevi\u0107","year":"2017","unstructured":"Milivojevi\u0107, Z., Savi\u0107, N., Brodi\u0107, D. (2017). Three-parametric cubic interpolation for estimating the fundamental frequency of the speech signal. Computing and Informatics, 36(2), 449\u2013469.","journal-title":"Computing and Informatics"},{"key":"1483_CR53","unstructured":"Ministry of Science And Technology Taiwan. (2018). Formosa grand challenge, talk to AI. https:\/\/fgc.stpi.narl.org.tw\/activity\/techai2018. Accessed 2019-01-26."},{"key":"1483_CR54","unstructured":"Mozilla. (2013). Common voice. https:\/\/voice.mozilla.org\/zh-TW. Accessed 2019-01-27."},{"key":"1483_CR55","unstructured":"Mozilla. (2018). Project DeepSpeech. https:\/\/github.com\/mozilla\/DeepSpeech. Accessed: 2019-01-28."},{"key":"1483_CR56","unstructured":"National Education Radio. (2018). National education radio. https:\/\/www.ner.gov.tw\/english. Accessed 2019-01-20."},{"key":"1483_CR57","unstructured":"National Statistics Taiwan. (2010). 2010 population and housing census in 2010. https:\/\/www.stat.gov.tw\/public\/Attachment\/21081884771.pdf. Accessed 2019-01-13."},{"key":"1483_CR58","unstructured":"Phonetics Laboratory. (2018). U.o.P.: the penn phonetics lab forced aligner. https:\/\/babel.ling.upenn.edu\/phonetics\/old_website_2015\/p2fa\/index.html. Accessed 2019-01-26."},{"key":"1483_CR59","doi-asserted-by":"publisher","unstructured":"Povey, D., Cheng, G., Wang, Y., Li, K., Xu, H., Yarmohamadi, M., Khudanpur, S. (2018). Semi-orthogonal low-rank matrix factorization for deep neural networks. In Interspeech 2018. https:\/\/doi.org\/10.21437\/Interspeech.2018-1417, http:\/\/www.danielpovey.com\/files\/2018_interspeech_tdnnf.pdf, (Vol. 2 pp. 3743\u20133747).","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"1483_CR60","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motl\u00ed\u010dek, P., Qian, Y., Schwarz, P., Silovsk\u2019y, J.S., Stemmer, G., Vesel\u2019y, K.V. (2011). The Kaldi speech recognition toolkit. In ASRU 2011. http:\/\/kaldi.sf.net\/."},{"key":"1483_CR61","doi-asserted-by":"publisher","unstructured":"Povey, D., Peddinti, V., Galvez, D., Ghahremani, P., Manohar, V., Na, X., Wang, Y., Khudanpur, S. (2016). Purely sequence-trained neural networks for ASR based on lattice-free MMI. In Proceedings of the annual conference of the international speech communication association, INTERSPEECH (pp. 2751\u20132755), DOI https:\/\/doi.org\/10.21437\/Interspeech.2016-595.","DOI":"10.21437\/Interspeech.2016-595"},{"key":"1483_CR62","unstructured":"Sak, H., Senior, A.W., Rao, K., Beaufays, F. (2015). Fast and accurate recurrent neural network acoustic models for speech recognition. In INTERSPEECH 2015, 16th annual conference of the international speech communication association, Dresden, Germany, September 6-10, 2015. http:\/\/www.isca-speech.org\/archive\/interspeech_2015\/i15_1468.html (pp. 1468\u20131472)."},{"key":"1483_CR63","unstructured":"SpeechOcean. (2018). Speech data services - text data and image data services - speech datasets database. http:\/\/en.speechocean.com\/. Accessed 2019-01-26."},{"key":"1483_CR64","unstructured":"Steering Committee for the Test Of Proficiency-Huayu. (2018). The test of Chinese as a foreign language (TOCFL). https:\/\/www.sc-top.org.tw\/english\/eng_index.php. Accessed 2019-01-26."},{"issue":"8","key":"1483_CR65","doi-asserted-by":"publisher","first-page":"1393","DOI":"10.1109\/TASLP.2018.2825432","volume":"26","author":"T Tan","year":"2018","unstructured":"Tan, T., Qian, Y., Hu, H., Zhou, Y., Ding, W., Yu, K. (2018). Adaptive very deep convolutional residual network for noise robust speech recognition. IEEE\/ACM Transactions on Audio Speech and Language Processing, 26 (8), 1393\u20131405. https:\/\/doi.org\/10.1109\/TASLP.2018.2825432.","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"issue":"8","key":"1483_CR66","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/JSTSP.2017.2752462","volume":"11","author":"H Tang","year":"2017","unstructured":"Tang, H., Lu, L., Kong, L., Gimpel, K., Livescu, K., Dyer, C., Smith, N.A., Renals, S. (2017). End-to-end neural segmental models for speech recognition. IEEE Journal on Selected Topics in Signal Processing, 11(8), 1254\u20131264. https:\/\/doi.org\/10.1109\/JSTSP.2017.2752462.","journal-title":"IEEE Journal on Selected Topics in Signal Processing"},{"key":"1483_CR67","unstructured":"The Association for Computational Linguistics and Chinese Language Processing. (2000). Database - the association for computational linguistics and chinese language processing. http:\/\/www.aclclp.org.tw\/corp.php. Accessed 2019-01-27."},{"key":"1483_CR68","unstructured":"The Association for Computational Linguistics and Chinese Language Processing. (2018). TCC300 Corpus. http:\/\/www.aclclp.org.tw\/use_mat.php#tcc300edu. Accessed 2019-01-27."},{"key":"1483_CR69","unstructured":"The Association for Computational Linguistics and Chinese Language Processing. (2018). The association for computational linguistics and chinese language processing. http:\/\/www.aclclp.org.tw. Accessed 2019-01-26."},{"key":"1483_CR70","unstructured":"The European Language Resources Association. (2018). ELRA-ELDA: the evaluations and language resources distribution agency. http:\/\/www.elra.info\/en\/. Accessed 2019-01- 26."},{"key":"1483_CR71","doi-asserted-by":"crossref","unstructured":"Wang, H.c., Seide, F., Tseng, C.y., Lee, L.s. (2000). Mat-2000 \u2013 design, collection, and validation of a Mandarin 2000-speaker telephone speech database. In InterSpeech (pp. 3\u20136).","DOI":"10.21437\/ICSLP.2000-848"},{"issue":"2","key":"1483_CR72","first-page":"219","volume":"10","author":"HM Wang","year":"2003","unstructured":"Wang, H.M. (2003). MATBN 2002: a Mandarin Chinese broadcast news corpus. ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition, 10(2), 219\u2013236.","journal-title":"ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition"},{"key":"1483_CR73","doi-asserted-by":"publisher","unstructured":"Wells, J.C. (1995). Computer-coding the IPA: a proposed extension of SAMPA. https:\/\/doi.org\/10.1179\/1362171811Y.0000000076, https:\/\/www.phon.ucl.ac.uk\/home\/sampa\/ipasam-x.pdf. Accessed 2019-01-26.","DOI":"10.1179\/1362171811Y.0000000076"},{"key":"1483_CR74","unstructured":"Wikipedia. (2018). Languages of Taiwan. http:\/\/www.ethnologue.com\/show_country.asp?name=Taiwan. Accessed 2019-01-27."},{"key":"1483_CR75","unstructured":"Wikipedia. (2018). Taiwanese Mandarin. https:\/\/en.wikipedia.org\/wiki\/Taiwanese_Mandarin. Accessed 2019-01-20."},{"key":"1483_CR76","unstructured":"Wu, M.c., Chen, W.y., Misbullah, A. (2018). Established a Taiwanese speech recognition system for formosa speech recognition challenge 2018. In Formosa speech recognition challenge workshop. https:\/\/drive.google.com\/file\/d\/15kKTG_w_jbx20vW1s_6rBAScXMAHYxd-."},{"key":"1483_CR77","doi-asserted-by":"publisher","unstructured":"Xiong, W., Droppo, J., Huang, X., Seide, F., Seltzer, M., Stolcke, A., Yu, D., Zweig, G. (2017). The Microsoft 2016 conversational speech recognition system. In ICASSP, IEEE International conference on acoustics, speech and signal processing - proceedings. https:\/\/doi.org\/10.1109\/ICASSP.2017.7953159, https:\/\/arxiv.org\/pdf\/1708.06073.pdf (pp. 5255\u20135259).","DOI":"10.1109\/ICASSP.2017.7953159"},{"issue":"4","key":"1483_CR78","doi-asserted-by":"publisher","first-page":"802","DOI":"10.1016\/j.csl.2011.03.001","volume":"25","author":"H Xu","year":"2011","unstructured":"Xu, H., Povey, D., Mangu, L., Zhu, J. (2011). Minimum Bayes Risk decoding and system combination based on a recursion for edit distance. Computer Speech & Language, 25(4), 802\u2013828. https:\/\/doi.org\/10.1016\/j.csl.2011.03.001.","journal-title":"Computer Speech & Language"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-019-01483-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-019-01483-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-019-01483-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,23]],"date-time":"2023-09-23T12:09:56Z","timestamp":1695470996000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-019-01483-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,28]]},"references-count":78,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2020,8]]}},"alternative-id":["1483"],"URL":"https:\/\/doi.org\/10.1007\/s11265-019-01483-4","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"type":"print","value":"1939-8018"},{"type":"electronic","value":"1939-8115"}],"subject":[],"published":{"date-parts":[[2019,11,28]]},"assertion":[{"value":"1 February 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 August 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}