{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T23:35:11Z","timestamp":1772148911297,"version":"3.50.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2018,12,15]],"date-time":"2018-12-15T00:00:00Z","timestamp":1544832000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"IEEE SIGHT"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1007\/s10772-018-09577-3","type":"journal-article","created":{"date-parts":[[2018,12,15]],"date-time":"2018-12-15T14:31:27Z","timestamp":1544884287000},"page":"111-119","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["A comparative study of deep neural network based Punjabi-ASR system"],"prefix":"10.1007","volume":"22","author":[{"given":"Virender","family":"Kadyan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Archana","family":"Mantri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R. K.","family":"Aggarwal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amitoj","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,12,15]]},"reference":[{"key":"9577_CR1","unstructured":"Acero, A., & Stern, R. M. (1992). Cepstral normalization for robust speech recognition. In Speech processing in adverse conditions."},{"key":"9577_CR2","volume-title":"Connectionist speech recognition. A hybrid approach","author":"H Bourlard","year":"1993","unstructured":"Bourlard, H., & Morgan, N. (1993). Connectionist speech recognition. A hybrid approach (Vol.\u00a0247). Boston: The Kluwer International Series in Engineering and Computer Science."},{"key":"9577_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., & Cheng, J. (2014). Deep neural network acoustic modeling for native and non-native Mandarin speech recognition. In Proceedings of ISCSLP (pp.\u00a06\u20139).","DOI":"10.1109\/ISCSLP.2014.6936617"},{"key":"9577_CR4","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-018-0828-x","author":"M Dua","year":"2018","unstructured":"Dua, M., Aggarwal, R. K., & Biswas, M. (2018). GFCC based discriminatively trained noise robust continuous ASR system for Hindi language. Journal of Ambient Intelligence and Humanized Computing. https:\/\/doi.org\/10.1007\/s12652-018-0828-x .","journal-title":"Journal of Ambient Intelligence and Humanized Computing"},{"issue":"4","key":"9577_CR5","first-page":"359","volume":"9","author":"M Dua","year":"2012","unstructured":"Dua, M., Aggarwal, R. K., Kadyan, V., & Dua, S. (2012). Punjabi automatic speech recognition using HTK. International Journal of Computer Science Issues, 9(4), 359\u2013364.","journal-title":"International Journal of Computer Science Issues"},{"key":"9577_CR6","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1006\/csla.1996.0013","volume":"10","author":"M Gales","year":"1996","unstructured":"Gales, M., & Woodland, P. (1996a). Mean and variance adaptation within the MLLR framework. Computer Speech & Language, 10, 249\u2013264.","journal-title":"Computer Speech & Language"},{"issue":"2","key":"9577_CR7","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1006\/csla.1998.0043","volume":"12","author":"MJ Gales","year":"1998","unstructured":"Gales, M. J. (1998). Maximum likelihood linear transformations for HMM-based speech recognition. Computer Speech & Language, 12(2), 75\u201398.","journal-title":"Computer Speech & Language"},{"issue":"14","key":"9577_CR8","doi-asserted-by":"publisher","first-page":"422","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), 422\u2013431.","journal-title":"International Journal of Computer Applications"},{"key":"9577_CR9","doi-asserted-by":"crossref","unstructured":"Haeb-Umbach, R., & Ney, H. (1992). Linear discriminant analysis for improved large vocabulary continuous speech recognition. In Acoustics, speech, and signal processing, 1992. ICASSP-92., 1992 IEEE international conference on (Vol.\u00a01, pp.\u00a013\u201316). IEEE.","DOI":"10.1109\/ICASSP.1992.225984"},{"key":"9577_CR10","doi-asserted-by":"crossref","unstructured":"Hermansky, H., Ellis, D. P., & Sharma, S. (2000). Tandem connectionist feature extraction for conventional HMM systems. In Acoustics, speech, and signal processing, 2000. ICASSP\u201900. Proceedings. 2000 IEEE international conference on (Vol.\u00a03, pp.\u00a01635\u20131638). IEEE.","DOI":"10.1109\/ICASSP.2000.862024"},{"issue":"6","key":"9577_CR11","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. E., Mohamed, A. R., Jaitly, N., & Kingsbury, B. (2012). Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine, 29(6), 82\u201397.","journal-title":"IEEE Signal Processing Magazine"},{"issue":"2","key":"9577_CR12","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1109\/TIT.1986.1057145","volume":"32","author":"BH Juang","year":"1986","unstructured":"Juang, B. H., Levinson, S., & Sondhi, M. (1986). Maximum likelihood estimation for multivariate mixture observations of markov chains (corresp.). IEEE Transactions on Information Theory, 32(2), 307\u2013309.","journal-title":"IEEE Transactions on Information Theory"},{"key":"9577_CR13","doi-asserted-by":"publisher","DOI":"10.1080\/03772063.2017.1369370","author":"V Kadyan","year":"2017","unstructured":"Kadyan, V., Mantri, A., & Aggarwal, R. K. (2017) Refinement of HMM model parameters for Punjabi Automatic Speech Recognition (PASR) System, IETE Journal of Research. https:\/\/doi.org\/10.1080\/03772063.2017.1369370 .","journal-title":"IETE Journal of Research"},{"key":"9577_CR14","doi-asserted-by":"publisher","DOI":"10.1080\/03772063.2017.1369370","author":"V Kadyan","year":"2017","unstructured":"Kadyan, V., Mantri, V., & Aggarwal, R. K. (2017) Refinement of HMM model parameters for Punjabi Automatic Speech Recognition (PASR) System. IETE Journal of Research. https:\/\/doi.org\/10.1080\/03772063.2017.1369370 .","journal-title":"IETE Journal of Research"},{"issue":"4","key":"9577_CR15","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1016\/S0167-6393(98)00061-2","volume":"26","author":"N Kumar","year":"1998","unstructured":"Kumar, N., & Andreou, A. G. (1998). Heteroscedastic discriminant analysis and reduced rank HMMs for improved speech recognition. Speech Communication, 26(4), 283\u2013297.","journal-title":"Speech Communication"},{"issue":"2","key":"9577_CR16","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1007\/s10772-017-9408-2","volume":"20","author":"Y Kumar","year":"2017","unstructured":"Kumar, Y., & Singh, N. (2017). An automatic speech recognition system for spontaneous Punjabi speech corpus. International Journal of Speech Technology, 20(2), 297\u2013303.","journal-title":"International Journal of Speech Technology"},{"key":"9577_CR17","unstructured":"Lata, S., & Arora, S. (2013) Laryngeal tonal characteristics of Punjabi\u2014An experimental study. In 2015 2nd international conference on computing for sustainable global development (pp.\u00a01694\u20131697)."},{"key":"9577_CR18","doi-asserted-by":"crossref","unstructured":"Liu, F., Stern, R. M., Huang, X., & Acero, R. (1993). Efficient cepstral normalization for robust speech recognition. In Proceedings of the workshop on human language technology (pp.\u00a069\u201374).","DOI":"10.3115\/1075671.1075688"},{"key":"9577_CR19","unstructured":"Matsoukas, S., Schwartz, R., Jin, H., & Nguyen, L. (1997). Practical implementations of speaker-adaptive training. In DARPA speech recognition workshop."},{"key":"9577_CR100","unstructured":"Mittal, S., & Sharma, R. K. (2014). Development of phonetic engine for Punjabi language (Doctoral dissertation), Thapar University, Patiala, India."},{"key":"9577_CR20","doi-asserted-by":"crossref","unstructured":"Mitra, V., Wang, W., Franco, H., Lei, Y., Bartels, C., & Graciarena, M. (2014). Evaluating robust features on deep neural networks for speech recognition in noisy and channel mismatched conditions. In Fifteenth annual conference of the international speech communication association.","DOI":"10.21437\/Interspeech.2014-224"},{"key":"9577_CR22","doi-asserted-by":"crossref","unstructured":"Palaz, D., & Collobert, R. (2015). Analysis of cnn-based speech recognition system using raw speech as input (No. EPFL-REPORT-210039). Idiap.","DOI":"10.21437\/Interspeech.2015-3"},{"key":"9577_CR23","doi-asserted-by":"crossref","unstructured":"Parthasarathi, S. H. K., Hoffmeister, B., Matsoukas, S., Mandal, A., Strom, N., & Garimella, S. (2015). fMLLR based feature-space speaker adaptation of DNN acoustic models. In Sixteenth annual conference of the international speech communication association.","DOI":"10.21437\/Interspeech.2015-720"},{"issue":"2","key":"9577_CR24","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1016\/j.csl.2010.06.003","volume":"25","author":"D Povey","year":"2011","unstructured":"Povey, D., Burget, L., Agarwal, M., Akyazi, P., Kai, F., Ghoshal, A., & Rose, R. C. (2011). The subspace Gaussian mixture model\u2014A structured model for speech recognition. Computer Speech & Language, 25(2), 404\u2013439.","journal-title":"Computer Speech & Language"},{"issue":"2","key":"9577_CR25","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"LR Rabiner","year":"1989","unstructured":"Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257\u2013286.","journal-title":"Proceedings of the IEEE"},{"key":"9577_CR26","volume-title":"Fundamentals of speech recognition","author":"LR Rabiner","year":"1993","unstructured":"Rabiner, L. R., & Juang, B. H. (1993). Fundamentals of speech recognition. Upper Saddle River: Prentice-Hall Inc."},{"key":"9577_CR27","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J Schmidhuber","year":"2015","unstructured":"Schmidhuber, J. (2015). Deep learning in neural networks: An overview. Neural Network, 61, 85\u2013117.","journal-title":"Neural Network"},{"key":"9577_CR28","unstructured":"Singh, A., Dipti, P., & Agrawal, S. S. (2015) Analysis of Punjabi tonemes. In Computing for Sustainable Global Development (INDIACom) (pp.\u00a01\u20136)."},{"key":"9577_CR29","doi-asserted-by":"crossref","unstructured":"Sivasankaran, S., Nugraha, A. A., Vincent, E., Morales-Cordovilla, J. A., Dalmia, S., Illina, I., et al. (2015). Robust ASR using neural network based speech enhancement and feature simulation. In IEEE workshop on automatic speech recognition and understanding (ASRU), 2015 (pp.\u00a0482\u2013489).","DOI":"10.1109\/ASRU.2015.7404834"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-018-09577-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-09577-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-09577-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T12:22:22Z","timestamp":1662639742000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-018-09577-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,15]]},"references-count":29,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["9577"],"URL":"https:\/\/doi.org\/10.1007\/s10772-018-09577-3","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,15]]},"assertion":[{"value":"21 January 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 November 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 December 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}