{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T14:08:25Z","timestamp":1742998105455,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031483110"},{"type":"electronic","value":"9783031483127"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-48312-7_21","type":"book-chapter","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:03:21Z","timestamp":1700597001000},"page":"258-270","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Direct Vs Cascaded Speech-to-Speech Translation Using Transformer"],"prefix":"10.1007","author":[{"given":"Lalaram","family":"Arya","sequence":"first","affiliation":[]},{"given":"Amartya","family":"Roy Chowdhury","sequence":"additional","affiliation":[]},{"given":"S. R. Mahadeva","family":"Prasanna","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"21_CR1","unstructured":"Languages of the world. https:\/\/www.ethnologue.com. Accessed 18 Sep 2023"},{"key":"21_CR2","unstructured":"Vanimedia. https:\/\/vanimedia.org\/wiki. Accessed 21 Sep 2023"},{"key":"21_CR3","doi-asserted-by":"publisher","first-page":"131858","DOI":"10.1109\/ACCESS.2021.3112535","volume":"9","author":"S Alhari","year":"2021","unstructured":"Alhari, S., et al.: Automatic speech recognition: systematic literature review. IEEE Access 9, 131858\u2013131876 (2021)","journal-title":"IEEE Access"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Arya, L., Agarwal, A., Mishra, J., Prasanna, S.R.M.: Analysis of layer-wise training in direct speech to speech translation using BI-LSTM. In: 2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA), pp. 1\u20136 (2022)","DOI":"10.1109\/O-COCOSDA202257103.2022.9997945"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Arya, L., Agarwal, A., Prasanna, S.R.M.: Investigation of data augmentation techniques for BI-LSTM based direct speech to speech translation. In: 2023 National Conference on Communications (NCC), pp. 1\u20136 (2020)","DOI":"10.1109\/NCC56989.2023.10067896"},{"key":"21_CR6","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems. vol. 33, pp. 12449\u201312460. Curran Associates, Inc. (2020)"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Chen, P.J., et al.: Speech-to-speech translation for a real-world unwritten language. In: Findings of the Association for Computational Linguistics: ACL 2023, pp. 4969\u20134983. Association for Computational Linguistics (2023)","DOI":"10.18653\/v1\/2023.findings-acl.307"},{"key":"21_CR8","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 (2018)","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Geng, M., et al.: Investigation of data augmentation techniques for disordered speech recognition. In: Interspeech 2020. ISCA (2020)","DOI":"10.21437\/Interspeech.2020-1161"},{"key":"21_CR10","unstructured":"Jia, Y., Ramanovich, M.T., Remez, T., Pomerantz, R.: Translatotron 2: high-quality direct speech-to-speech translation with voice preservation. In: Proceedings of the 39th International Conference on Machine Learning. vol. 162, pp. 10120\u201310134. PMLR (17\u201323 Jul 2022)"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Jia, Y., et al.: Direct speech-to-speech translation with a sequence-to-sequence model. In: INTERSPEECH, pp. 1123\u20131127 (2019)","DOI":"10.21437\/Interspeech.2019-1951"},{"key":"21_CR12","unstructured":"Kim, J., Kim, S., Kong, J., Yoon, S.: Glow-TTS: a generative flow for text-to-speech via monotonic alignment search. In: Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS\u201920 (2020)"},{"key":"21_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, Conference Track Proceedings (2015)"},{"key":"21_CR14","unstructured":"Kong, J., Kim, J., Bae, J.: HiFi-GAN: generative adversarial networks for efficient and high fidelity speech synthesis. In: Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS\u201920 (2020)"},{"key":"21_CR15","unstructured":"LeCun, Y., Bengio, Y.: Convolutional networks for images, speech, and time series, pp. 255\u2013258, MIT Press (1998)"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Lee, A., et al.: Direct speech-to-speech translation with discrete units. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 3327\u20133339. Association for Computational Linguistics (2022)","DOI":"10.18653\/v1\/2022.acl-long.235"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Li, N., Liu, S., Liu, Y., Zhao, S., Liu, M.: Neural speech synthesis with transformer network. In: Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence. AAAI\u201919, AAAI Press (2019)","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Li, X., Jia, Y., Chiu, C.C.: Textless direct speech-to-speech translation with discrete speech representation. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10096797"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Park, D., et al.: Specaugment: a simple data augmentation method for automatic speech recognition. In: Interspeech, pp. 2613\u20132617. ISCA (09 2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Post, M.: A call for clarity in reporting BLEU scores. In: Proceedings of the Third Conference on Machine Translation: Research Papers, pp. 186\u2013191. Association for Computational Linguistics, Brussels, Belgium (2018)","DOI":"10.18653\/v1\/W18-6319"},{"key":"21_CR21","unstructured":"Sandhan, J., Daksh, A., Paranjay, O.A., Behera, L., Goyal, P.: Prabhupadavani: a code-mixed speech translation data for 25 languages. LaTeCH-CLfL, pp. 24\u201329 (2022)"},{"key":"21_CR22","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/j.patrec.2019.12.019","volume":"131","author":"S Shahnawazuddin","year":"2020","unstructured":"Shahnawazuddin, S., Adiga, N., Kathania, H.K., Sai, B.T.: Creating speaker independent ASR system through prosody modification based data augmentation. Pattern Recogn. Lett. 131, 213\u2013218 (2020)","journal-title":"Pattern Recogn. Lett."},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Shen, J., et al..: Natural tts synthesis by conditioning wavenet on mel spectrogram predictions. In: 2018 IEEE International Conference on Acoustics, Speech nd Signal Processing (ICASSP), pp. 4779\u20134783 (2018)","DOI":"10.1109\/ICASSP.2018.8461368"},{"issue":"4","key":"21_CR24","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1016\/S1007-0214(08)70086-5","volume":"13","author":"T Shimizu","year":"2008","unstructured":"Shimizu, T., Ashikari, Y., Sumita, E., Zhang, J., Nakamura, S.: NICT\/ATR Chinese-Japanese-English speech-to-speech translation system. Tsinghua Sci. Technol. 13(4), 540\u2013544 (2008)","journal-title":"Tsinghua Sci. Technol."},{"key":"21_CR25","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/j.aiopen.2020.11.001","volume":"1","author":"Z Tan","year":"2020","unstructured":"Tan, Z., et al.: Neural machine translation: a review of methods, resources, and tools. AI Open 1, 5\u201321 (2020)","journal-title":"AI Open"},{"key":"21_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems. vol. 30. Curran Associates, Inc. (2017)"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, C., Tan, X., Ren, Y., Qin, T., jun Zhang, K., Liu, T.Y.: Uwspeech: speech to speech translation for unwritten languages. In: AAAI Conference on Artificial Intelligence, pp. 14319\u201314327 (2020)","DOI":"10.1609\/aaai.v35i16.17684"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-48312-7_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:06:21Z","timestamp":1700597181000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-48312-7_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031483110","9783031483127"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-48312-7_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 November 2023","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":"Dharwad","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iitdh.ac.in\/specom-2023\/","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":"174","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":"94","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":"54% - 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)"}}]}}