{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T06:39:17Z","timestamp":1764225557378,"version":"3.37.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030412982"},{"type":"electronic","value":"9783030412999"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-41299-9_45","type":"book-chapter","created":{"date-parts":[[2020,2,22]],"date-time":"2020-02-22T04:02:51Z","timestamp":1582344171000},"page":"580-593","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A Generative Adversarial Network Based Ensemble Technique for Automatic Evaluation of Machine Synthesized Speech"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3739-9495","authenticated-orcid":false,"given":"Jaynil","family":"Jaiswal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8463-0012","authenticated-orcid":false,"given":"Ashutosh","family":"Chaubey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1090-4375","authenticated-orcid":false,"given":"Sasi Kiran Reddy","family":"Bhimavarapu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7500-9120","authenticated-orcid":false,"given":"Shashank","family":"Kashyap","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4318-1353","authenticated-orcid":false,"given":"Puneet","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6277-6267","authenticated-orcid":false,"given":"Balasubramanian","family":"Raman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5735-5254","authenticated-orcid":false,"given":"Partha Pratim","family":"Roy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,2,23]]},"reference":[{"key":"45_CR1","unstructured":"Arik, S.\u00d6., et al.: Deep voice: real-time neural text-to-speech. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 195\u2013204. JMLR.org (2017)"},{"key":"45_CR2","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Tacotron: towards end-to-end speech synthesis. arXiv preprint \narXiv:1703.10135\n\n (2017)","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"45_CR3","unstructured":"Ping, W.: Deep voice 3: scaling text-to-speech with convolutional sequence learning. arXiv preprint \narXiv:1710.07654\n\n (2017)"},{"key":"45_CR4","unstructured":"van den Oord, A., et al.: Wavenet: a generative model for raw audio. arXiv preprint \narXiv:1609.03499\n\n (2016)"},{"issue":"4","key":"45_CR5","first-page":"650","volume":"82","author":"PL Salza","year":"1996","unstructured":"Salza, P.L., Foti, E., Nebbia, L., Oreglia, M.: MOS and pair comparison combined methods for quality evaluation of text-to-speech systems. Acta Acust. United Acust. 82(4), 650\u2013656 (1996)","journal-title":"Acta Acust. United Acust."},{"key":"45_CR6","first-page":"15236","volume":"07","author":"P Ghate","year":"2017","unstructured":"Ghate, P., Shirbahadurkar, S.D.: A survey on methods of TTS and various test for evaluating the quality of synthesized speech. Int. J. Dev. Res. 07, 15236\u201315239 (2017)","journal-title":"Int. J. Dev. Res."},{"key":"45_CR7","unstructured":"Ito, K.: The LJ speech dataset (2017)"},{"key":"45_CR8","unstructured":"Veaux, C., Yamagishi, J., MacDonald, K., et al.: CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit. University of Edinburgh, The Centre for Speech Technology Research (CSTR) (2017)"},{"issue":"5","key":"45_CR9","doi-asserted-by":"publisher","first-page":"e0196391","DOI":"10.1371\/journal.pone.0196391","volume":"13","author":"SR Livingstone","year":"2018","unstructured":"Livingstone, S.R., Russo, F.A.: The Ryerson audio-visual database of emotional speech and song (RAVDESS): a dynamic, multimodal set of facial and vocal expressions in North American English. PloS One 13(5), e0196391 (2018)","journal-title":"PloS One"},{"issue":"4","key":"45_CR10","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso, C., et al.: IEMOCAP: interactive emotional dyadic motion capture database. Lang. Resour. Eval. 42(4), 335 (2008)","journal-title":"Lang. Resour. Eval."},{"issue":"5","key":"45_CR11","doi-asserted-by":"publisher","first-page":"670","DOI":"10.1002\/hed.23956","volume":"38","author":"RC Dwivedi","year":"2016","unstructured":"Dwivedi, R.C., et al.: Acoustic parameters of speech: lack of correlation with perceptual and questionnaire-based speech evaluation in patients with oral and oropharyngeal cancer treated with primary surgery. Head Neck 38(5), 670\u2013676 (2016)","journal-title":"Head Neck"},{"key":"45_CR12","doi-asserted-by":"crossref","unstructured":"Sebastian, R.J., Ryan, E.B.: Speech cues and social evaluation: markers of ethnicity, social class, and age. In: Recent Advances in Language, Communication, and Social Psychology, pp. 112\u2013143. Routledge (2018)","DOI":"10.4324\/9780429436178-5"},{"key":"45_CR13","unstructured":"Tyagi, V., Ganapathiraju, A., Wyss, F.I.: Method and system for selectively biased linear discriminant analysis in automatic speech recognition systems. US Patent 9,679,556, 13 June 2017"},{"key":"45_CR14","unstructured":"Chorowski, J.K., Bahdanau, D., Serdyuk, D., Cho, K., Bengio, Y.: Attention-based models for speech recognition. In: Advances in Neural Information Processing Systems, pp. 577\u2013585 (2015)"},{"key":"45_CR15","unstructured":"Gajic, B., Narayanan, S.S., Parthasarathy, S., Rose, R.C., Rosenberg, A.E.: System and method of performing user-specific automatic speech recognition. US Patent 9,058,810, 16 June 2015"},{"key":"45_CR16","unstructured":"Renals, S.: Automatic Speech Recognition-ASR Lecture: Multilingual Speech Recognition (2017)"},{"key":"45_CR17","doi-asserted-by":"crossref","unstructured":"Russell, M., Cook, A.: Experimental evaluation of duration modelling techniques for automatic speech recognition. In: ICASSP 1987, IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 12, pp. 2376\u20132379. IEEE (1987)","DOI":"10.1109\/ICASSP.1987.1169918"},{"key":"45_CR18","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1016\/j.csl.2016.11.003","volume":"46","author":"AH Moore","year":"2017","unstructured":"Moore, A.H., Parada, P.P., Naylor, P.A.: Speech enhancement for robust automatic speech recognition: evaluation using a baseline system and instrumental measures. Comput. Speech Lang. 46, 574\u2013584 (2017)","journal-title":"Comput. Speech Lang."},{"key":"45_CR19","unstructured":"Otani, T., Togawa, T., Nakayama, S.: Speech evaluation apparatus and speech evaluation method. US Patent App. 15\/703,249, 29 March 2018"},{"key":"45_CR20","doi-asserted-by":"crossref","unstructured":"Sailor, H.B., Patil, H.A.: Fusion of magnitude and phase-based features for objective evaluation of TTS voice. In: The 9th International Symposium on Chinese Spoken Language Processing, pp. 521\u2013525. IEEE (2014)","DOI":"10.1109\/ISCSLP.2014.6936618"},{"key":"45_CR21","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"45_CR22","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint \narXiv:1411.1784\n\n (2014)"},{"key":"45_CR23","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2014). \narxiv:1412.6980\n\n. Comment: Published as a Conference Paper at the 3rd International Conference for Learning Representations, San Diego (2015)"},{"key":"45_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR, abs\/1512.03385 (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"45_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"45_CR26","doi-asserted-by":"crossref","unstructured":"An, S., Ling, Z., Dai, L.: Emotional statistical parametric speech synthesis using LSTM-RNNs. In: 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 1613\u20131616. IEEE (2017)","DOI":"10.1109\/APSIPA.2017.8282282"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-41299-9_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,22]],"date-time":"2020-02-22T04:12:28Z","timestamp":1582344748000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-41299-9_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030412982","9783030412999"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-41299-9_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"23 February 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2019a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.acpr2019.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"214","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"125","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"58% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"for ACPR 2019 Workshops volume accepted 17 full papers and 6 short papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}