{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T21:51:59Z","timestamp":1743112319492,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":36,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811536069"},{"type":"electronic","value":"9789811536076"}],"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"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","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\/978-981-15-3607-6_3","type":"book-chapter","created":{"date-parts":[[2020,5,22]],"date-time":"2020-05-22T11:03:09Z","timestamp":1590145389000},"page":"33-43","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Toward Lexicon-Free Bangla Automatic Speech Recognition System"],"prefix":"10.1007","author":[{"given":"Md.","family":"Mehadi Hasan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Md.","family":"Ariful Islam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shafkat","family":"Kibria","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Shahidur","family":"Rahman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,5,23]]},"reference":[{"key":"3_CR1","unstructured":"Openslr-large bengali ASR training data set. Google Inc. http:\/\/www.openslr.org\/53\/"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Abdel-Hamid O, Mohamed AR, Jiang H, Deng L, Penn G, Yu D (2014) Convolutional neural networks for speech recognition. IEEE\/ACM Trans Audio Speech Lang Process 22(10):1533\u20131545","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Ahmed A, Hifny Y, Shaalan K, Toral S (2016) Lexicon free Arabic speech recognition recipe. In: International conference on advanced intelligent systems and informatics. Springer, Cham, pp 147\u2013159 (2016)","DOI":"10.1007\/978-3-319-48308-5_15"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Ali MNY, Al-Mamun SA, Das JK, Nurannabi AM (2008) Morphological analysis of Bangla words for universal networking language. In: 2008 third international conference on digital information management. IEEE, pp 532\u2013537","DOI":"10.1109\/ICDIM.2008.4746734"},{"key":"3_CR5","doi-asserted-by":"publisher","unstructured":"Alif Al\u00a0Amin M, Towhidul\u00a0Islam M, Kibria S, Shahidur\u00a0Rahman M (2019) Continuous Bengali speech recognition based on deep neural network, pp 1\u20136. https:\/\/doi.org\/10.1109\/ECACE.2019.8679341","DOI":"10.1109\/ECACE.2019.8679341"},{"key":"3_CR6","unstructured":"Amodei D, Ananthanarayanan S, Anubhai R, Bai J, Battenberg E, Case C, Casper J, Catanzaro B, Cheng Q, Chen G, et\u00a0al (2016) Deep speech 2: end-to-end speech recognition in english and mandarin. In: International conference on machine learning, pp 173\u2013182"},{"key":"3_CR7","unstructured":"Bills A, David A, Dubinski E, Fiscus J, Gillies B, Harpe M, Jarrett A, Encarnaci\u00f3n M, Molina P, Ray J, Rytting A, Paget S, Shen W, Silber R, Tzoukermann E, Wong J (2016) IARPA-babel103b-v0.4b LDC2016S08. Web Download. Linguistic Data Consortium, Philadelphia. https:\/\/catalog.ldc.upenn.edu\/LDC2016S08 (2016)"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Chan W, Jaitly N, Le Q, Vinyals O (2016) Listen, attend and spell: a neural network for large vocabulary conversational speech recognition. In: 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 4960\u20134964","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"3_CR9","unstructured":"Chorowski J, Bahdanau D, Serdyuk D, Cho K, Bengio Y (2015) Attention-based models for speech recognition. In: Advances in neural information processing systems"},{"key":"3_CR10","unstructured":"Das A, Bandyopadhyay S (2010) Morphological stemming cluster identification for Bangla. In: Knowledge sharing event-1: task, vol 3"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Das B, Mandal S, Mitra P (2011) Bengali speech corpus for continuous automatic speech recognition system. In: 2011 International conference on speech database and assessments (Oriental COCOSDA). IEEE, pp 51\u201355","DOI":"10.1109\/ICSDA.2011.6085979"},{"key":"3_CR12","unstructured":"Graves A (2012) Sequence transduction with recurrent neural networks. arXiv:1211.3711"},{"key":"3_CR13","unstructured":"Hannun A, Case C, Casper J, Catanzaro B, Diamos G, Elsen E, Prenger R, Satheesh S, Sengupta S, Coates A, et\u00a0al (2014) Deep speech: scaling up end-to-end speech recognition. arXiv:1412.5567"},{"key":"3_CR14","unstructured":"Hasnat M, Molwa J, Khan M (2007) Isolated and continuous Bangla speech recognition: implementation. Performance and application perspective"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Hinton G, Deng L, Yu D, Dahl GE, Mohamed AR, Jaitly N, Senior A, Vanhoucke V, Nguyen P, Sainath TN, et\u00a0al (2012) Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process Mag 29(6):82\u201397","DOI":"10.1109\/MSP.2012.2205597"},{"key":"3_CR16","unstructured":"Hossain M, Rahman M, Prodhan UK, Khan M, et\u00a0al (2013) Implementation of back-propagation neural network for isolated Bangla speech recognition. arXiv:1308.3785"},{"issue":"1","key":"3_CR17","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1145\/2500887","volume":"57","author":"X Huang","year":"2014","unstructured":"Huang X, Baker J, Reddy R (2014) A historical perspective of speech recognition. Commun ACM 57(1):94\u2013103","journal-title":"Commun ACM"},{"key":"3_CR18","unstructured":"Islam M (2009) Research on Bangla language processing in Bangladesh: progress and challenges. In: 8th international language & development conference, pp 23\u201325"},{"key":"3_CR19","unstructured":"Jaitly N, Le QV, Vinyals O, Sutskever I, Sussillo D, Bengio S (2016) An online sequence-to-sequence model using partial conditioning. In: Advances in neural information processing systems, pp 5067\u20135075"},{"key":"3_CR20","unstructured":"Juang BH, Rabiner LR (2005) Automatic speech recognition\u2013a brief history of the technology development. Georgia Institute of Technology. Atlanta Rutgers University and the University of California. Santa Barbara, vol 1, p 67"},{"key":"3_CR21","unstructured":"Karim R, Rahman MS, Iqbal MZ (2002) Recognition of spoken letters in Bangla. In: Proceedings of the 5th international conference on computer and information technology (ICCIT02)"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Nahid MMH, Islam MA, Islam MS (2016) A noble approach for recognizing Bangla real number automatically using CMU Sphinx4. In: 2016 5th international conference on informatics, electronics and vision (ICIEV). IEEE, pp 844\u2013849","DOI":"10.1109\/ICIEV.2016.7760121"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Nahid MMH, Purkaystha B, Islam MS (2017) Bengali speech recognition: a double layered LSTM-RNN approach. In: 2017 20th international conference of computer and information technology (ICCIT). IEEE, pp. 1\u20136","DOI":"10.1109\/ICCITECHN.2017.8281848"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Paul AK, Das D, Kamal MM (2009) Bangla speech recognition system using LPC and ANN. In: 2009. ICAPR\u201909. Seventh international conference on, advances in pattern recognition. IEEE, pp 171\u2013174","DOI":"10.1109\/ICAPR.2009.80"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Qian Y, Woodland PC (2016) Very deep convolutional neural networks for robust speech recognition. In: 2016 IEEE on spoken language technology workshop (SLT). IEEE, pp 481\u2013488","DOI":"10.1109\/SLT.2016.7846307"},{"key":"3_CR26","unstructured":"Raffel C, Luong MT, Liu PJ, Weiss RJ, Eck D (2017) Online and linear-time attention by enforcing monotonic alignments. arXiv:1704.00784"},{"key":"3_CR27","unstructured":"Rahman K, Hossain M, Das D, Islam T, Ali M (2003) Continuous Bangla speech recognition system. In: Proceedings of the 6th international conference on computer and information technology (ICCIT03)"},{"key":"3_CR28","doi-asserted-by":"publisher","unstructured":"Rahman Saurav J, Amin S, Kibria S, Shahidur Rahman M (2018) Bangla speech recognition for voice search. In: 2018 international conference on Bangla speech and language processing (ICBSLP), pp 1\u20134. https:\/\/doi.org\/10.1109\/ICBSLP.2018.8554944","DOI":"10.1109\/ICBSLP.2018.8554944"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Rath SP, Povey D, Vesel\u00fd K, Cernock\u00fd J (2013) Improved feature processing for deep neural networks, pp 109\u2013113","DOI":"10.21437\/Interspeech.2013-48"},{"issue":"5","key":"3_CR30","first-page":"17","volume":"47","author":"PP Shrishrimal","year":"2012","unstructured":"Shrishrimal PP, Deshmukh RR, Waghmare VB (2012) Indian language speech database: a review. Int J Comput Appl 47(5):17\u201321","journal-title":"Int J Comput Appl"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Sinha S, Jain A, Agrawal SS (2014) Speech processing for hindi dialect recognition. In: Advances in signal processing and intelligent recognition systems. Springer, Cham, pp 161\u2013169","DOI":"10.1007\/978-3-319-04960-1_14"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Stolcke A (2002) Srilm-an extensible language modeling toolkit. In: Seventh international conference on spoken language processing","DOI":"10.21437\/ICSLP.2002-303"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Sultana S, Akhand M, Das PK, Rahman MH (2012) Bangla speech-to-text conversion using SAPI. In: 2012 international conference on computer and communication engineering (ICCCE). IEEE, pp 385\u2013390","DOI":"10.1109\/ICCCE.2012.6271216"},{"key":"3_CR34","unstructured":"Sumit SH, Al\u00a0Muntasir T, Zaman MA, Nandi RN, Sourov T (2018) Noise robust end-to-end speech recognition for Bangla language. In: 2018 international conference on Bangla speech and language processing (ICBSLP). IEEE, pp 1\u20135"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Zhang Y, Chan W, Jaitly N (2017) Very deep convolutional networks for end-to-end speech recognition. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 4845\u20134849","DOI":"10.1109\/ICASSP.2017.7953077"},{"key":"3_CR36","unstructured":"Zhang Y, Pezeshki M, Brakel P, Zhang S, Bengio CLY, Courville A (2017) Towards end-to-end speech recognition with deep convolutional neural networks. arXiv:1701.02720"}],"container-title":["Algorithms for Intelligent Systems","Proceedings of International Joint Conference on Computational Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-15-3607-6_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,24]],"date-time":"2022-10-24T16:16:12Z","timestamp":1666628172000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-981-15-3607-6_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9789811536069","9789811536076"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-981-15-3607-6_3","relation":{},"ISSN":["2524-7565","2524-7573"],"issn-type":[{"type":"print","value":"2524-7565"},{"type":"electronic","value":"2524-7573"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"23 May 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}