{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T03:19:07Z","timestamp":1743045547420,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031209796"},{"type":"electronic","value":"9783031209802"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20980-2_41","type":"book-chapter","created":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T19:03:09Z","timestamp":1668279789000},"page":"477-493","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multi-modal Approach to\u00a0Mining Intent from\u00a0Code-Mixed Hindi-English Calls in\u00a0the\u00a0Hyperlocal-Delivery Domain"],"prefix":"10.1007","author":[{"given":"Jose","family":"Mathew","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pranjal","family":"Sahu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhavuk","family":"Singhal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aniket","family":"Joshi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Krishna Reddy","family":"Medikonda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jairaj","family":"Sathyanarayana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,10]]},"reference":[{"key":"41_CR1","unstructured":"Ai4bharat group. https:\/\/ai4bharat.org\/"},{"key":"41_CR2","unstructured":"Al-Rfou\u2019, R., Perozzi, B., Skiena, S.: Polyglot: Distributed word representations for multilingual NLP. In: Proceedings of the Seventeenth Conference on Computational Natural Language Learning, pp. 183\u2013192. Association for Computational Linguistics, Sofia, Bulgaria (2013). https:\/\/aclanthology.org\/W13-3520"},{"key":"41_CR3","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. Advances in Neural Information Processing Systems, vol. 33, pp. 12449\u201312460 (2020)"},{"key":"41_CR4","unstructured":"blenz, V.: Speech enhancement with deep learning (2020). https:\/\/github.com\/vbelz\/Speech-enhancement\/tree\/b6056c6ac745f88b00779d1083eceddfda1efb43"},{"key":"41_CR5","doi-asserted-by":"crossref","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information (2016), CoRR abs\/ arXiv:1607.04606","DOI":"10.1162\/tacl_a_00051"},{"key":"41_CR6","volume-title":"Connectionist Speech Recognition: A Hybrid Approach","author":"HA Bourlard","year":"2012","unstructured":"Bourlard, H.A., Morgan, N.: Connectionist Speech Recognition: A Hybrid Approach, vol. 247. Springer Science & Business Media, Berlin (2012)"},{"key":"41_CR7","doi-asserted-by":"crossref","unstructured":"Braun, S., Tashev, I.: Data augmentation and loss normalization for deep noise suppression. In: International Conference on Speech and Computer, pp. 79\u201386. Springer (2020)","DOI":"10.1007\/978-3-030-60276-5_8"},{"key":"41_CR8","doi-asserted-by":"crossref","unstructured":"Chiu, C.C., Sainath, T.N., Wu, Y., Prabhavalkar, R., Nguyen, P., Chen, Z., Kannan, A., Weiss, R.J., Rao, K., Gonina, E., et al.: State-of-the-art speech recognition with sequence-to-sequence models. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4774\u20134778. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462105"},{"issue":"6","key":"41_CR9","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1121\/1.1906946","volume":"24","author":"KH Davis","year":"1952","unstructured":"Davis, K.H., Biddulph, R., Balashek, S.: Automatic recognition of spoken digits. J. Acoust. Soc. Am. 24(6), 637\u2013642 (1952)","journal-title":"J. Acoust. Soc. Am."},{"key":"41_CR10","unstructured":"D\u00e9fossez, A., Usunier, N., Bottou, L., Bach, F.: Music source separation in the waveform domain (2019). arXiv preprint arXiv:1911.13254"},{"key":"41_CR11","doi-asserted-by":"crossref","unstructured":"Dong, L., Xu, S., Xu, B.: Speech-transformer: a no-recurrence sequence-to-sequence model for speech recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5884\u20135888. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"41_CR12","doi-asserted-by":"crossref","unstructured":"Graves, A.: Sequence transduction with recurrent neural networks (2012). arXiv preprint arXiv:1211.3711","DOI":"10.1007\/978-3-642-24797-2"},{"key":"41_CR13","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"41_CR14","doi-asserted-by":"crossref","unstructured":"Gulati, A., Qin, J., Chiu, C.C., Parmar, N., Zhang, Y., Yu, J., Han, W., Wang, S., Zhang, Z., Wu, Y., et al.: Conformer: Convolution-augmented transformer for speech recognition (2020). arXiv preprint arXiv:2005.08100","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"41_CR15","unstructured":"Heafield, K.: Kenlm (2021). https:\/\/github.com\/kpu\/kenlm"},{"key":"41_CR16","doi-asserted-by":"crossref","unstructured":"Javed, T., Doddapaneni, S., Raman, A., Bhogale, K.S., Ramesh, G., Kunchukuttan, A., Kumar, P., Khapra, M.M.: Towards building asr systems for the next billion users. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 10813\u201310821 (2022)","DOI":"10.1609\/aaai.v36i10.21327"},{"issue":"1","key":"41_CR17","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","volume":"33","author":"H Jegou","year":"2010","unstructured":"Jegou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. IEEE Trans. Pattern Anal. Mach. Intell. 33(1), 117\u2013128 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"41_CR18","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1109\/PROC.1976.10159","volume":"64","author":"F Jelinek","year":"1976","unstructured":"Jelinek, F.: Continuous speech recognition by statistical methods. Proc. IEEE 64(4), 532\u2013556 (1976)","journal-title":"Proc. IEEE"},{"key":"41_CR19","doi-asserted-by":"crossref","unstructured":"Kakwani, D., Kunchukuttan, A., Golla, S., N.C., G., Bhattacharyya, A., Khapra, M.M., Kumar, P.: IndicNLPSuite: Monolingual corpora, evaluation benchmarks and pre-trained multilingual language models for Indian languages. In: Findings of EMNLP (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.445"},{"key":"41_CR20","unstructured":"Kuchaiev, O., Li, J., Nguyen, H., Hrinchuk, O., Leary, R., Ginsburg, B., Kriman, S., Beliaev, S., Lavrukhin, V., Cook, J., et al.: Nemo: a toolkit for building ai applications using neural modules(2019). arXiv preprint arXiv:1909.09577"},{"key":"41_CR21","unstructured":"Kunchukuttan, A., Kakwani, D., Golla, S., N.C., G., Bhattacharyya, A., Khapra, M.M., Kumar, P.: Ai4bharat-indicnlp corpus: Monolingual corpora and word embeddings for indic languages (2020). arXiv preprint arXiv:2005.00085"},{"issue":"4","key":"41_CR22","doi-asserted-by":"publisher","first-page":"1035","DOI":"10.1002\/j.1538-7305.1983.tb03114.x","volume":"62","author":"SE Levinson","year":"1983","unstructured":"Levinson, S.E., Rabiner, L.R., Sondhi, M.M.: An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition. Bell Syst. Tech. J. 62(4), 1035\u20131074 (1983)","journal-title":"Bell Syst. Tech. J."},{"key":"41_CR23","doi-asserted-by":"crossref","unstructured":"Li, J., Lavrukhin, V., Ginsburg, B., Leary, R., Kuchaiev, O., Cohen, J.M., Nguyen, H., Gadde, R.T.: Jasper: An end-to-end convolutional neural acoustic model (2019). arXiv preprint arXiv:1904.03288","DOI":"10.21437\/Interspeech.2019-1819"},{"key":"41_CR24","doi-asserted-by":"crossref","unstructured":"Park, D.S., Zhang, Y., Chiu, C.C., Chen, Y., Li, B., Chan, W., Le, Q.V., Wu, Y.: Specaugment on large scale datasets. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6879\u20136883. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053205"},{"issue":"10","key":"41_CR25","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1008228","volume":"16","author":"T Sainburg","year":"2020","unstructured":"Sainburg, T., Thielk, M., Gentner, T.Q.: Finding, visualizing, and quantifying latent structure across diverse animal vocal repertoires. PLoS Comput. Biol. 16(10), e1008228 (2020)","journal-title":"PLoS Comput. Biol."},{"key":"41_CR26","doi-asserted-by":"crossref","unstructured":"Song, X., Wang, G., Wu, Z., Huang, Y., Su, D., Yu, D., Meng, H.: Speech-xlnet: unsupervised acoustic model pretraining for self-attention networks (2019). arXiv preprint arXiv:1910.10387","DOI":"10.21437\/Interspeech.2020-1511"},{"key":"41_CR27","unstructured":"Technologies, K.: Pyctc decoder (2021). https:\/\/github.com\/kensho-technologies\/pyctcdecode"},{"key":"41_CR28","doi-asserted-by":"crossref","unstructured":"Tian, Z., Yi, J., Bai, Y., Tao, J., Zhang, S., Wen, Z.: Synchronous transformers for end-to-end speech recognition. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7884\u20137888. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054260"},{"key":"41_CR29","doi-asserted-by":"crossref","unstructured":"Wang, Y., Mohamed, A., Le, D., Liu, C., Xiao, A., Mahadeokar, J., Huang, H., Tjandra, A., Zhang, X., Zhang, F., et al.: Transformer-based acoustic modeling for hybrid speech recognition. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6874\u20136878. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054345"},{"key":"41_CR30","doi-asserted-by":"publisher","unstructured":"Westhausen, N.L., Meyer, B.T.: Dual-Signal Transformation LSTM Network for Real-Time Noise Suppression. In: Proceedings of Interspeech 2020, pp. 2477\u20132481 (2020). https:\/\/doi.org\/10.21437\/Interspeech. 2020\u20132631","DOI":"10.21437\/Interspeech"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20980-2_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T19:07:56Z","timestamp":1668280076000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20980-2_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031209796","9783031209802"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20980-2_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"10 November 2022","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":"Gurugram","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.specom.co.in","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"99","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":"60","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":"61% - 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":"4","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)"}}]}}