{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:26:55Z","timestamp":1740122815423,"version":"3.37.3"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,12,11]],"date-time":"2015-12-11T00:00:00Z","timestamp":1449792000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100002183","name":"Department of Electronics and Information Technology, Ministry of Communications and Information Technology (IN)","doi-asserted-by":"publisher","award":["11(6)\/2011-HCC(TDIL)"],"award-info":[{"award-number":["11(6)\/2011-HCC(TDIL)"]}],"id":[{"id":"10.13039\/501100002183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1007\/s10772-015-9329-x","type":"journal-article","created":{"date-parts":[[2015,12,11]],"date-time":"2015-12-11T07:25:11Z","timestamp":1449818711000},"page":"121-134","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Articulatory and excitation source features for speech recognition in read, extempore and conversation modes"],"prefix":"10.1007","volume":"19","author":[{"given":"K. E.","family":"Manjunath","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"K.","family":"Sreenivasa Rao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,12,11]]},"reference":[{"key":"9329_CR1","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4615-3210-1","volume-title":"Connnectionist speech recognition: A hybrid approach","author":"HA Bourlard","year":"1994","unstructured":"Bourlard, H. A., & Morgan, N. (1994). Connnectionist speech recognition: A hybrid approach. Dordrecht: Kluwer."},{"key":"9329_CR2","doi-asserted-by":"crossref","unstructured":"Chengalvarayan, R. (1998). On the use of normalized LPC error towards better large vocabulary speech recognition systems. In IEEE international conference on acoustics, speech and signal processing (pp. 17\u201320).","DOI":"10.1109\/ICASSP.1998.674356"},{"key":"9329_CR3","doi-asserted-by":"crossref","unstructured":"Dhananjaya, N., Yegnanarayana, B., & Suryakanth, V. G. (2011). Acoustic-phonetic information from excitation source for refining manner hypotheses of a phone recognizer. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 5252\u20135255).","DOI":"10.1109\/ICASSP.2011.5947542"},{"key":"9329_CR4","doi-asserted-by":"crossref","unstructured":"Fallside, F., Lucke, H., Marsland, T. P., O\u2019Shea, P. J., Owen, M. S. J., Prager, R. W., et al. (1990). Continuous speech recognition for the TIMIT database using neural networks. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 445\u2013448).","DOI":"10.1109\/ICASSP.1990.115745"},{"key":"9329_CR5","unstructured":"Gerfen. (2015). Phonetics theory (online). http:\/\/www.unc.edu\/~gerfen\/Ling 30Sp2002\/phonetics.html ."},{"key":"9329_CR6","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A., & Hinton, G. (2013). Speech recognition with deep recurrent neural networks. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 1\u20135).","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"9329_CR7","unstructured":"He, J., Liu, L., & Palm, G. (1996). On the use of residual cepstrum in speech recognition. In IEEE international conference on acoustics, speech, and signal processing (ICASSP) (pp. 5\u20138)."},{"key":"9329_CR8","doi-asserted-by":"crossref","unstructured":"Hermansky, H., Ellis, D. P. W., & Sharma, S. (2000). Tandem connectionist feature extraction for conventional HMM systems. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 1635\u20131638).","DOI":"10.1109\/ICASSP.2000.862024"},{"key":"9329_CR9","doi-asserted-by":"crossref","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., Jaitly, N., et al. (2012). Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Processing Magazine, 29, 82\u201397.","journal-title":"IEEE Signal Processing Magazine"},{"key":"9329_CR10","doi-asserted-by":"crossref","unstructured":"Ketabdar, H., & Bourlard, H. (2008). Hierarchical integration of phonetic and lexical knowledge in phone posterior estimation. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 4065\u20134068).","DOI":"10.1109\/ICASSP.2008.4518547"},{"key":"9329_CR11","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/S0167-6393(01)00020-6","volume":"37","author":"K Kirchhoff","year":"2002","unstructured":"Kirchhoff, K., Fink, Gernot A., & Sagerer, Gerhard. (2002). Combining acoustic and articulatory feature information for robust speech recognition. Speech Communication, 37, 303\u2013319.","journal-title":"Speech Communication"},{"key":"9329_CR12","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1109\/29.46546","volume":"37","author":"K Lee","year":"1989","unstructured":"Lee, K., & Hon, H. (1989). Speaker-independent phone recognition using hidden Markov models. IEEE Transactions on Acoustics, Speech and Signal Processing, 37, 1641\u20131648.","journal-title":"IEEE Transactions on Acoustics, Speech and Signal Processing"},{"key":"9329_CR13","doi-asserted-by":"crossref","unstructured":"Manjunath, K. E., & Sreenivasa Rao, K. (2014). Automatic phonetic transcription for read, extempore and conversation speech for an indian language: Bengali. In IEEE national conference on communications (NCC) (pp. 1\u20136).","DOI":"10.1109\/NCC.2014.6811347"},{"key":"9329_CR14","doi-asserted-by":"crossref","unstructured":"Manjunath, K. E., & Sreenivasa Rao, K. (2015a). Source and system features for phone recognition. International Journal of Speech Technology, 18, 257\u2013270.","DOI":"10.1007\/s10772-014-9266-0"},{"key":"9329_CR15","unstructured":"Manjunath, K. E., & Sreenivasa Rao, K. (2015b). Improvement of phone recognition accuracy using articulatory features. Applied Soft Computing (revision submitted)."},{"key":"9329_CR16","doi-asserted-by":"crossref","unstructured":"Manjunath, K. E., Sreenivasa Rao, K., & Gurunath Reddy, M. (2015a). Two-stage phone recognition system using articulatory and spectral features. In IEEE international conference on signal processing and communication engineering systems (SPACES) (pp. 107\u2013111).","DOI":"10.1109\/SPACES.2015.7058226"},{"key":"9329_CR17","doi-asserted-by":"crossref","unstructured":"Manjunath, K. E., Sreenivasa Rao, K., & Gurunath Reddy, M. (2015b). Improvement of phone recognition accuracy using source and system features. In IEEE international conference on signal processing and communication engineering systems (SPACES) (pp. 501\u2013505).","DOI":"10.1109\/SPACES.2015.7058205"},{"key":"9329_CR18","doi-asserted-by":"crossref","unstructured":"Manjunath, K. E., Sreenivasa Rao, K., & Pati, D. (2013). Development of phonetic engine for Indian languages: Bengali and Oriya. In 16th International oriental COCOSDA conference (IEEE explore) (pp. 1\u20136), Gurgoan, India.","DOI":"10.1109\/ICSDA.2013.6709900"},{"key":"9329_CR19","doi-asserted-by":"crossref","unstructured":"Manjunath, K. E., Sunil Kumar, S. B., Pati, D., Satapathy, B., & Sreenivasa Rao, K. (2013). Development of consonant-vowel recognition systems for Indian languages: Bengali and Oriya. In IEEE INDICON (IEEE Explore) (pp. 1\u20136), IIT Bombay, Mumbai, India.","DOI":"10.1109\/INDCON.2013.6726109"},{"key":"9329_CR20","unstructured":"Metze, F. (2005). Articulatory features for conversational speech recognition. Ph.D. dissertation, Carnegie Mellon University."},{"key":"9329_CR21","doi-asserted-by":"crossref","unstructured":"Mitra, V., Wang, W., Stolcke, A., Nam, H., Richey, C., Yuan, J., et al. (2013). Articulatory trajectories for large-vocabulary speech recognition. In IEEE international conference on acoustics, speech, and signal processing (ICASSP) (pp. 7145\u20137149).","DOI":"10.1109\/ICASSP.2013.6639049"},{"key":"9329_CR22","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1109\/TASL.2011.2109382","volume":"20","author":"A Mohamed","year":"2012","unstructured":"Mohamed, A., Dahl, G. E., & Hinton, G. (2012). Acoustic modeling using deep belief networks. IEEE Transactions on Audio, Speech, and Language Processing, 20, 14\u201322.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9329_CR23","doi-asserted-by":"crossref","unstructured":"Sainath, T. N., Mohamed, A., Kingsbury, B., & Ramabhadran, B. (2013). Deep convolutional neural networks for LVCSR. In IEEE international conference on acoustics, speech, and signal processing (ICASSP) (pp. 8614\u20138618).","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"9329_CR24","doi-asserted-by":"crossref","first-page":"1139","DOI":"10.1016\/j.specom.2009.05.004","volume":"51","author":"SM Siniscalchi","year":"2009","unstructured":"Siniscalchi, S. M., & Lee, C. (2009). A study on integrating acoustic-phonetic information into lattice rescoring for automatic speech recognition. Speech Communication, 51, 1139\u20131153.","journal-title":"Speech Communication"},{"key":"9329_CR25","unstructured":"Speech Group at the International Computer Science Ins. (2010). QuickNet software and documentation (online). http:\/\/www1.icsi.berkeley.edu\/Speech ."},{"key":"9329_CR26","unstructured":"Sreenivasa Rao, K., & Koolagudi, S. G. (2013). Recognition of emotions from video using acoustic and facial features. In Signal, image and video processing (SIViP) (pp. 1\u201317)."},{"key":"9329_CR27","unstructured":"Sunil Kumar, S. B., Sreenivasa Rao, K., & Pati, D. (2013). Phonetic and prosodically rich transcribed speech corpus in indian languages: Bengali and Odia. In 16th International Oriental COCOSDA (pp. 1\u20135)."},{"key":"9329_CR28","unstructured":"The Hidden Markov Model Toolkit and HTK book. (2015). (online). http:\/\/htk.eng.cam.ac.uk ."},{"key":"9329_CR29","unstructured":"The International Phonetic Association. (2015). International Phonetic Alphabet (online). http:\/\/www.langsci.ucl.ac.uk\/ipa\/index.html ."},{"key":"9329_CR30","doi-asserted-by":"crossref","unstructured":"Toth, L. (2014). Convolutional deep maxout networks for phone recognition. In International speech communication association (INTERSPEECH) (pp. 1078\u20131082).","DOI":"10.21437\/Interspeech.2014-278"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-015-9329-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-015-9329-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-015-9329-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,29]],"date-time":"2022-05-29T00:14:14Z","timestamp":1653783254000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-015-9329-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12,11]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,3]]}},"alternative-id":["9329"],"URL":"https:\/\/doi.org\/10.1007\/s10772-015-9329-x","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2015,12,11]]}}}