{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T15:05:32Z","timestamp":1743001532719,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030377335"},{"type":"electronic","value":"9783030377342"}],"license":[{"start":{"date-parts":[[2019,12,24]],"date-time":"2019-12-24T00:00:00Z","timestamp":1577145600000},"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\/978-3-030-37734-2_5","type":"book-chapter","created":{"date-parts":[[2019,12,27]],"date-time":"2019-12-27T00:03:00Z","timestamp":1577404980000},"page":"52-62","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Inferring Emphasis for Real Voice Data: An Attentive Multimodal Neural Network Approach"],"prefix":"10.1007","author":[{"given":"Suping","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Jia","family":"Jia","sequence":"additional","affiliation":[]},{"given":"Long","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yanfeng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Fanbo","family":"Meng","sequence":"additional","affiliation":[]},{"given":"Fei","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Jialie","family":"Shen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,12,24]]},"reference":[{"key":"5_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Brenier, J.M., Cer, D.M., Jurafsky, D.: The detection of emphatic words using acoustic and lexical features. In: Ninth European Conference on Speech Communication and Technology (2005)","DOI":"10.21437\/Interspeech.2005-576"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Cernak, M., Honnet, P.E.: An empirical model of emphatic word detection. In: Interspeech, pp. 573\u2013577 (2015)","DOI":"10.21437\/Interspeech.2015-206"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Chen, J.Y., Lan, W.: Automatic lexical stress detection for Chinese learners\u2019 of English. In: International Symposium on Chinese Spoken Language Processing (2011)","DOI":"10.1109\/ISCSLP.2010.5684859"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Yuan, J., You, Q., Luo, J.: Twitter sentiment analysis via bi-sense emoji embedding and attention-based LSTM. arXiv preprint arXiv:1807.07961 (2018)","DOI":"10.1145\/3240508.3240533"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Do, Q.T., Takamichi, S., Sakti, S., Neubig, G., Toda, T., Nakamura, S.: Preserving word-level emphasis in speech-to-speech translation using linear regression HSMMs. In: Sixteenth Annual Conference of the International Speech Communication Association (2015)","DOI":"10.21437\/Interspeech.2015-727"},{"issue":"3","key":"5_CR7","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1109\/TASLP.2016.2643280","volume":"25","author":"QT Do","year":"2017","unstructured":"Do, Q.T., Toda, T., Neubig, G., Sakti, S., Nakamura, S.: Preserving word-level emphasis in speech-to-speech translation. IEEE\/ACM Trans. Audio Speech Lang. Process. 25(3), 544\u2013556 (2017)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Fan, Y., Qian, Y., Xie, F.L., Soong, F.K.: TTS synthesis with bidirectional LSTM based recurrent neural networks. In: Fifteenth Annual Conference of the International Speech Communication Association (2014)","DOI":"10.21437\/Interspeech.2014-443"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Ferrer, L., Bratt, H., Richey, C., Franco, H., Abrash, V., Precoda, K.: Lexical stress classification for language learning using spectral and segmental features. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 7704\u20137708 (2014)","DOI":"10.1109\/ICASSP.2014.6855099"},{"issue":"Aug","key":"5_CR10","first-page":"115","volume":"3","author":"FA Gers","year":"2002","unstructured":"Gers, F.A., Schraudolph, N.N., Schmidhuber, J.: Learning precise timing with LSTM recurrent networks. J. Mach. Learn. Res. 3(Aug), 115\u2013143 (2002)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR11","unstructured":"Heldner, M.: Spectral emphasis as an additional source of information in accent detection. In: ISCA Tutorial and Research Workshop (ITRW) on Prosody in Speech Recognition and Understanding (2001)"},{"key":"5_CR12","unstructured":"Kennedy, L.S., Ellis, D.P.W.: Pitch-based emphasis detection for characterization of meeting recordings. In: 2003 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2003, pp. 243\u2013248 (2003)"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Kim, Y.: Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882 (2014)","DOI":"10.3115\/v1\/D14-1181"},{"key":"5_CR14","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"issue":"3","key":"5_CR15","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1006\/jpho.1997.0046","volume":"25","author":"DR Ladd","year":"1997","unstructured":"Ladd, D.R., Morton, R.: The perception of intonational emphasis: continuous or categorical? J. Phon. 25(3), 313\u2013342 (1997)","journal-title":"J. Phon."},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Li, L., Wu, Z., Xu, M., Meng, H.M., Cai, L.: Combining CNN and BLSTM to extract textual and acoustic features for recognizing stances in mandarin ideological debate competition. In: Interspeech, pp. 1392\u20131396 (2016)","DOI":"10.21437\/Interspeech.2016-324"},{"issue":"4","key":"5_CR17","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1162\/coli.2009.35.4.35403","volume":"35","author":"Z Li","year":"2009","unstructured":"Li, Z., Sun, M.: Punctuation as implicit annotations for Chinese word segmentation. Comput. Linguist. 35(4), 505\u2013512 (2009)","journal-title":"Comput. Linguist."},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Ning, Y., et al.: Learning cross-lingual knowledge with multilingual BLSTM for emphasis detection with limited training data. In: ICASSP 2017\u20132017 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 5615\u20135619 (2017)","DOI":"10.1109\/ICASSP.2017.7953231"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Schnall, A., Heckmann, M.: Integrating sequence information in the audio-visual detection of word prominence in a human-machine interaction scenario. In: Fifteenth Annual Conference of the International Speech Communication Association (2014)","DOI":"10.1109\/IJCNN.2015.7280639"},{"issue":"11","key":"5_CR20","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Sig. Process. 45(11), 2673\u20132681 (1997)","journal-title":"IEEE Trans. Sig. Process."},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, L., et al.: Emphasis detection for voice dialogue applications using multi-channel convolutional bidirectional long short-term memory network. In: 2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP), pp. 210\u2013214. IEEE (2018)","DOI":"10.1109\/ISCSLP.2018.8706625"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Zhou, S., Jia, J., Wang, Q., Dong, Y., Yin, Y., Lei, K.: Inferring emotion from conversational voice data: a semi-supervised multi-path generative neural network approach. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11280"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-37734-2_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,9]],"date-time":"2022-10-09T11:28:54Z","timestamp":1665314934000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-37734-2_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,24]]},"ISBN":["9783030377335","9783030377342"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-37734-2_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019,12,24]]},"assertion":[{"value":"24 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 January 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 January 2020","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":"mmm2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.mmm2020.kr\/","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":"171","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":"40","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":"23% - 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":"5","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":"Of the 171 submissions, 46 were accepted as poster papers; of the 49 special session paper submissions, 28 were accepted for oral presentation and 8 for poster presentation; 9 demo papers and 10 VBS papers were also accepted.","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)"}}]}}