{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T08:09:53Z","timestamp":1767773393891},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,5,20]],"date-time":"2020-05-20T00:00:00Z","timestamp":1589932800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,5,20]],"date-time":"2020-05-20T00:00:00Z","timestamp":1589932800000},"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":["Int J Speech Technol"],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1007\/s10772-020-09717-8","type":"journal-article","created":{"date-parts":[[2020,5,20]],"date-time":"2020-05-20T15:03:58Z","timestamp":1589987038000},"page":"41-45","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["DNN based continuous speech recognition system of Punjabi language on Kaldi toolkit"],"prefix":"10.1007","volume":"24","author":[{"given":"Jyoti","family":"Guglani","sequence":"first","affiliation":[]},{"given":"A. N.","family":"Mishra","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,5,20]]},"reference":[{"key":"9717_CR1","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1016\/j.csl.2015.05.005","volume":"36","author":"L Badino","year":"2016","unstructured":"Badino, L., Canevari, C., Fadiga, L., & Metta, G. (2016). Integrating articulatory data in deep neural network-based acoustic modeling. Computer Speech & Language, 36, 173\u2013195. https:\/\/doi.org\/10.1016\/j.csl.2015.05.005.","journal-title":"Computer Speech & Language"},{"key":"9717_CR2","doi-asserted-by":"publisher","unstructured":"Cosi, P. (n.d.). Phone Recognition Experiments on ArtiPhon with KALDI. EVALITA. Evaluation of NLP and Speech Tools for Italian (pp.\u00a026\u201331). https:\/\/doi.org\/10.4000\/books.aaccademia.1932","DOI":"10.4000\/books.aaccademia.1932"},{"key":"9717_CR3","doi-asserted-by":"publisher","unstructured":"Cosi, P. (2015). A KALDI-DNN-based ASR system for Italian. In 2015 International Joint Conference on Neural Networks (IJCNN). https:\/\/doi.org\/10.1109\/ijcnn.2015.7280336","DOI":"10.1109\/ijcnn.2015.7280336"},{"issue":"1","key":"9717_CR4","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/tasl.2011.2134090","volume":"20","author":"GE Dahl","year":"2012","unstructured":"Dahl, G. E., Dong, Yu, Deng, Li, & Acero, A. (2012). Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Transactions on Audio, Speech, and Language Processing, 20(1), 30\u201342. https:\/\/doi.org\/10.1109\/tasl.2011.2134090.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9717_CR5","doi-asserted-by":"publisher","unstructured":"Dua, M., Kadyan, V., Aggarwal, R. K., & Dua, S. (2012). Punjabi speech to text system for connected words. Fourth International Conference on Advances in Recent Technologies in Communication and Computing (ARTCom2012). https:\/\/doi.org\/10.1049\/cp.2012.2528","DOI":"10.1049\/cp.2012.2528"},{"key":"9717_CR6","doi-asserted-by":"publisher","unstructured":"Erdogan, H., Hershey, J. R., Watanabe, S., & Le Roux, J. (2015). Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks. In 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https:\/\/doi.org\/10.1109\/icassp.2015.7178061.","DOI":"10.1109\/icassp.2015.7178061"},{"issue":"14","key":"9717_CR7","doi-asserted-by":"publisher","first-page":"23","DOI":"10.5120\/12563-9002","volume":"72","author":"W Ghai","year":"2013","unstructured":"Ghai, W., & Singh, N. (2013). Continuous speech recognition for Punjabi language. International Journal of Computer Applications, 72(14), 23\u201328. https:\/\/doi.org\/10.5120\/12563-9002.","journal-title":"International Journal of Computer Applications"},{"issue":"6","key":"9717_CR8","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/msp.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A., Jaitly, N., et al. (2012a). Deep neural networks for acoustic modeling in speech recognition: The shared views of Four Research Groups. IEEE Signal Processing Magazine, 29(6), 82\u201397. https:\/\/doi.org\/10.1109\/msp.2012.2205597.","journal-title":"IEEE Signal Processing Magazine"},{"issue":"6","key":"9717_CR9","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/msp.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A., Jaitly, N., et al. (2012b). Deep neural networks for acoustic modeling in speech recognition: The shared views of Four Research Groups. IEEE Signal Processing Magazine, 29(6), 82\u201397. https:\/\/doi.org\/10.1109\/msp.2012.2205597.","journal-title":"IEEE Signal Processing Magazine"},{"key":"9717_CR10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-45510-5_56","author":"A Horndasch","year":"2016","unstructured":"Horndasch, A., Kaufhold, C., & N\u00f6th, E. (2016). How to add word classes to the Kaldi Speech Recognition Toolkit. Lecture Notes in Computer Science. https:\/\/doi.org\/10.1007\/978-3-319-45510-5_56.","journal-title":"Lecture Notes in Computer Science"},{"key":"9717_CR11","doi-asserted-by":"publisher","first-page":"72845","DOI":"10.1109\/access.2018.2881096","volume":"6","author":"AH Meftah","year":"2018","unstructured":"Meftah, A. H., Alotaibi, Y. A., & Selouani, S.-A. (2018). Evaluation of an Arabic Speech Corpus of emotions: A perceptual and statistical analysis. IEEE Access, 6, 72845\u201372861. https:\/\/doi.org\/10.1109\/access.2018.2881096.","journal-title":"IEEE Access"},{"key":"9717_CR12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-595","author":"D Povey","year":"2016","unstructured":"Povey, D., Peddinti, V., Galvez, D., Ghahremani, P., Manohar, V., Na, X., et al. (2016). Purely sequence-trained neural networks for ASR based on lattice-free MMI. Interspeech. https:\/\/doi.org\/10.21437\/interspeech.2016-595.","journal-title":"Interspeech"},{"key":"9717_CR13","doi-asserted-by":"publisher","unstructured":"Seide, F., Li, G., Chen, X., & Yu, D. (2011). Feature engineering in Context-Dependent Deep Neural Networks for conversational speech transcription. In 2011 IEEE Workshop on Automatic Speech Recognition & Understanding. https:\/\/doi.org\/10.1109\/asru.2011.6163899","DOI":"10.1109\/asru.2011.6163899"},{"key":"9717_CR14","doi-asserted-by":"publisher","unstructured":"Sigtia, S., & Dixon, S. (2014). Improved music feature learning with deep neural networks. In 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https:\/\/doi.org\/10.1109\/icassp.2014.6854949","DOI":"10.1109\/icassp.2014.6854949"},{"key":"9717_CR15","doi-asserted-by":"publisher","unstructured":"Tang, H., Hasegawa-Johnson, M., & Huang, T. S. (2010). Toward robust learning of the Gaussian mixture state emission densities for hidden Markov models. In 2010 IEEE International Conference on Acoustics, Speech and Signal Processing. https:\/\/doi.org\/10.1109\/icassp.2010.5494989","DOI":"10.1109\/icassp.2010.5494989"},{"key":"9717_CR16","doi-asserted-by":"publisher","unstructured":"Upadhyaya, P., Farooq, O., Abidi, M. R., & Varshney, Y. V. (2017). Continuous Hindi speech recognition model based on Kaldi ASR toolkit. In 2017 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET). https:\/\/doi.org\/10.1109\/wispnet.2017.8299868","DOI":"10.1109\/wispnet.2017.8299868"},{"key":"9717_CR17","doi-asserted-by":"publisher","unstructured":"Vesely, K., Hannemann, M., & Burget, L. (2013). Semi-supervised training of Deep Neural Networks. In 2013 IEEE Workshop on Automatic Speech Recognition and Understanding. https:\/\/doi.org\/10.1109\/asru.2013.6707741","DOI":"10.1109\/asru.2013.6707741"},{"key":"9717_CR18","doi-asserted-by":"publisher","unstructured":"Vu, N. T., Imseng, D., Povey, D., Motlicek, P., Schultz, T., & Bourlard, H. (2014). Multilingual deep neural network based acoustic modeling for rapid language adaptation. In 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https:\/\/doi.org\/10.1109\/icassp.2014.6855086","DOI":"10.1109\/icassp.2014.6855086"},{"key":"9717_CR19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-911","author":"JHM Wong","year":"2016","unstructured":"Wong, J. H. M., & Gales, M. J. F. (2016). Sequence student-teacher training of deep neural networks. Interspeech. https:\/\/doi.org\/10.21437\/interspeech.2016-911.","journal-title":"Interspeech"},{"key":"9717_CR20","unstructured":"Woodland, P. C., Gales, M. J. F., Pye, D., & Young, S. J. (n.d.). Broadcast news transcription using HTK. 1997"},{"key":"9717_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/bs.host.2018.05.001","author":"Y Xie","year":"2018","unstructured":"Xie, Y., Le, L., Zhou, Y., & Raghavan, V. V. (2018). Deep learning for natural language processing. Computational Analysis and Understanding of Natural Languages: Principles, Methods and Applications. https:\/\/doi.org\/10.1016\/bs.host.2018.05.001.","journal-title":"Computational Analysis and Understanding of Natural Languages: Principles, Methods and Applications"},{"key":"9717_CR22","doi-asserted-by":"publisher","unstructured":"Zhang, X., Trmal, J., Povey, D., & Khudanpur, S. (2014). Improving deep neural network acoustic models using generalized maxout networks. In 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https:\/\/doi.org\/10.1109\/icassp.2014.6853589","DOI":"10.1109\/icassp.2014.6853589"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-020-09717-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-020-09717-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-020-09717-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,20]],"date-time":"2021-05-20T07:53:03Z","timestamp":1621497183000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-020-09717-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,20]]},"references-count":22,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,3]]}},"alternative-id":["9717"],"URL":"https:\/\/doi.org\/10.1007\/s10772-020-09717-8","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5,20]]},"assertion":[{"value":"20 July 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}