{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:30:37Z","timestamp":1767339037010,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,2,22]],"date-time":"2019-02-22T00:00:00Z","timestamp":1550793600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,2,22]]},"DOI":"10.1145\/3318299.3318385","type":"proceedings-article","created":{"date-parts":[[2019,5,16]],"date-time":"2019-05-16T12:10:25Z","timestamp":1558008625000},"page":"52-58","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["A Study on the Performance Evaluation of Machine Learning Models for Phoneme Classification"],"prefix":"10.1145","author":[{"given":"Ali Shariq","family":"Imran","sequence":"first","affiliation":[{"name":"Department of Electronic Systems, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"}]},{"given":"Abdolreza Sabzi","family":"Shahrebabaki","sequence":"additional","affiliation":[{"name":"Department of Electronic Systems, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"}]},{"given":"Negar","family":"Olfati","sequence":"additional","affiliation":[{"name":"Department of Electronic Systems, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"}]},{"given":"Torbj\u00f8rn","family":"Svendsen","sequence":"additional","affiliation":[{"name":"Department of Electronic Systems, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"}]}],"member":"320","published-online":{"date-parts":[[2019,2,22]]},"reference":[{"volume-title":"Phoneme recognizer based on long temporal context,\" Speech Processing Group","author":"Schwarz P.","key":"e_1_3_2_1_1_1","unstructured":"P. Schwarz , P. Matejka , L. Burget , and O. Glembek , \" Phoneme recognizer based on long temporal context,\" Speech Processing Group , Faculty of Information Technology, Brno University of Technology .{Online}. Available: http:\/\/speech.fit.vutbr.cz\/en\/software, 2006. P. Schwarz, P. Matejka, L. Burget, and O. Glembek, \"Phoneme recognizer based on long temporal context,\" Speech Processing Group, Faculty of Information Technology, Brno University of Technology.{Online}. Available: http:\/\/speech.fit.vutbr.cz\/en\/software, 2006."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758119"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"B. Kingsbury T. N. Sainath and H. Soltau \"Scalable minimum bayes risk training of deep neural network acoustic models using distributed hessian-free optimization \" in 13th Annual Conference of the International Speech Communication Association (InterSpeech 2012) pp. 10--13 ISCA September 2012.  B. Kingsbury T. N. Sainath and H. Soltau \"Scalable minimum bayes risk training of deep neural network acoustic models using distributed hessian-free optimization \" in 13th Annual Conference of the International Speech Communication Association (InterSpeech 2012) pp. 10--13 ISCA September 2012.","DOI":"10.21437\/Interspeech.2012-3"},{"key":"e_1_3_2_1_6_1","first-page":"1","volume-title":"ICML'12","author":"Yu D.","year":"2012","unstructured":"D. Yu , F. Seide , and G. Li , \" Conversational speech transcription using context-dependent deep neural networks,\" in Proceedings of the 29th International Conference on Machine Learning , ICML'12 , pp. 1 -- 2 , Omnipress , August 2012 . D. Yu, F. Seide, and G. Li, \"Conversational speech transcription using context-dependent deep neural networks,\" in Proceedings of the 29th International Conference on Machine Learning, ICML'12, pp. 1--2, Omnipress, August 2012."},{"key":"e_1_3_2_1_7_1","first-page":"8604","volume-title":"Speech and Signal Processing","author":"Deng L.","year":"2013","unstructured":"L. Deng , J. Li , J.-T. Huang , K. Yao , D. Yu , F. Seide , M. Seltzer , G. Zweig , X. He , J. Williams , Y. Gong , and A. Acero , \" Recent advances in deep learning for speech research at microsoft,\" in 2013 IEEE International Conference on Acoustics , Speech and Signal Processing , pp. 8604 -- 8608 , 2013 . Exported from https:\/\/app.dimensions.ai on 2018\/12\/18. L. Deng, J. Li, J.-T. Huang, K. Yao, D. Yu, F. Seide, M. Seltzer, G. Zweig, X. He, J. Williams, Y. Gong, and A. Acero, \"Recent advances in deep learning for speech research at microsoft,\" in 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 8604--8608, 2013. Exported from https:\/\/app.dimensions.ai on 2018\/12\/18."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1080\/02564602.2015.1010611"},{"key":"e_1_3_2_1_9_1","first-page":"1","volume-title":"Deep learning in acoustic modeling for automatic speech recognition and understanding-an overview,\" in 2015 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","author":"Gavat I.","year":"2015","unstructured":"I. Gavat and D. Militaru , \" Deep learning in acoustic modeling for automatic speech recognition and understanding-an overview,\" in 2015 International Conference on Speech Technology and Human-Computer Dialogue (SpeD) , pp. 1 -- 8 , IEEE , October 2015 . I. Gavat and D. Militaru, \"Deep learning in acoustic modeling for automatic speech recognition and understanding-an overview,\" in 2015 International Conference on Speech Technology and Human-Computer Dialogue (SpeD), pp. 1--8, IEEE, October 2015."},{"key":"e_1_3_2_1_10_1","volume-title":"ISCA","author":"Deng L.","year":"2014","unstructured":"L. Deng and J. C. Platt , \" Ensemble deep learning for speech recognition,\" in Fifteenth Annual Conference of the International Speech Communication Association (InterSpeech 2014), pp. 1915--1919 , ISCA , September 2014 . L. Deng and J. C. Platt, \"Ensemble deep learning for speech recognition,\" in Fifteenth Annual Conference of the International Speech Communication Association (InterSpeech 2014), pp. 1915--1919, ISCA, September 2014."},{"key":"e_1_3_2_1_11_1","volume-title":"ISCA","author":"Jaitly N.","year":"2012","unstructured":"N. Jaitly , P. Nguyen , A. Senior , and V. Vanhoucke , \" Application of pretrained deep neural networks to large vocabulary speech recognition,\" in Thirteenth Annual Conference of the International Speech Communication Association (InterSpeech 2012) , ISCA , September 2012 . N. Jaitly, P. Nguyen, A. Senior, and V. Vanhoucke, \"Application of pretrained deep neural networks to large vocabulary speech recognition,\" in Thirteenth Annual Conference of the International Speech Communication Association (InterSpeech 2012), ISCA, September 2012."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2009.932166"},{"key":"e_1_3_2_1_13_1","first-page":"176","volume-title":"Acoustic feature comparison for different speaking rates,\" in Human-Computer Interaction. Interaction Technologies","author":"Shahrebabaki A. S.","year":"2018","unstructured":"A. S. Shahrebabaki , A. S. Imran , N. Olfati , and T. Svendsen , \" Acoustic feature comparison for different speaking rates,\" in Human-Computer Interaction. Interaction Technologies (M. Kurosu, ed.), (Cham), pp. 176 -- 189 , Springer International Publishing , June 2018 . A. S. Shahrebabaki, A. S. Imran, N. Olfati, and T. Svendsen, \"Acoustic feature comparison for different speaking rates,\" in Human-Computer Interaction. Interaction Technologies (M. Kurosu, ed.), (Cham), pp. 176--189, Springer International Publishing, June 2018."},{"key":"e_1_3_2_1_14_1","volume-title":"IEEE Signal Processing Society","author":"Povey D.","year":"2011","unstructured":"D. Povey , A. Ghoshal , G. Boulianne , N. Goel , M. Hannemann , Y. Qian , P. Schwarz , and G. Stemmer , \" The KALDI speech recognition toolkit,\" in IEEE 2011 Workshop on Automatic Speech Recognition and Understanding , IEEE Signal Processing Society , December 2011 . D. Povey, A. Ghoshal, G. Boulianne, N. Goel, M. Hannemann, Y. Qian, P. Schwarz, and G. Stemmer, \"The KALDI speech recognition toolkit,\" in IEEE 2011 Workshop on Automatic Speech Recognition and Understanding, IEEE Signal Processing Society, December 2011."},{"key":"e_1_3_2_1_15_1","first-page":"265","volume-title":"Tensorflow: A system for large-scale machine learning,\" in 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)","author":"Abadi M.","year":"2016","unstructured":"M. Abadi , P. Barham , J. Chen , Z. Chen , A. Davis , J. Dean , M. Devin , S. Ghemawat , G. Irving , M. Isard , M. Kudlur , J. Levenberg , R. Monga , S. Moore , D. G. Murray , B. Steiner , P. Tucker , V. Vasudevan , P. Warden , M. Wicke , Y. Yu , and X. Zheng , \" Tensorflow: A system for large-scale machine learning,\" in 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16) , pp. 265 -- 283 , August 2016 . M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, M. Kudlur, J. Levenberg, R. Monga, S. Moore, D. G. Murray, B. Steiner, P. Tucker, V. Vasudevan, P. Warden, M. Wicke, Y. Yu, and X. Zheng, \"Tensorflow: A system for large-scale machine learning,\" in 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), pp. 265--283, August 2016."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143865"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"e_1_3_2_1_18_1","first-page":"1233","volume-title":"Feature frame stacking in RNN-based tandem ASR systems-learned vs. predefined context,\" in Twelfth Annual Conference of the International Speech Communication Association (InterSpeech","author":"W\u00f6llmer M.","year":"2011","unstructured":"M. W\u00f6llmer , B. Schuller , and G. Rigoll , \" Feature frame stacking in RNN-based tandem ASR systems-learned vs. predefined context,\" in Twelfth Annual Conference of the International Speech Communication Association (InterSpeech 2011 ), pp. 1233 -- 1236 , ISCA , August 2011. M. W\u00f6llmer, B. Schuller, and G. Rigoll, \"Feature frame stacking in RNN-based tandem ASR systems-learned vs. predefined context,\" in Twelfth Annual Conference of the International Speech Communication Association (InterSpeech 2011), pp. 1233--1236, ISCA, August 2011."},{"key":"e_1_3_2_1_19_1","volume-title":"ISCA","author":"Salomon J.","year":"2002","unstructured":"J. Salomon , S. King , and J. Salomon , \" Framewise phone classification using support vector machines,\" in Seventh International Conference on Spoken Language Processing, pp. 2645--2648 , ISCA , September 2002 . J. Salomon, S. King, and J. Salomon, \"Framewise phone classification using support vector machines,\" in Seventh International Conference on Spoken Language Processing, pp. 2645--2648, ISCA, September 2002."},{"key":"e_1_3_2_1_20_1","volume-title":"Spoken language processing: a guide to theory, algorithm, and system development","author":"Huang X.","year":"2001","unstructured":"X. Huang , A. Acero , and H.-W. Hon , Spoken language processing: a guide to theory, algorithm, and system development . Upper Saddle River, NJ, USA : Prentice Hall PTR , 1 st ed., 2001 . X. Huang, A. Acero, and H.-W. Hon, Spoken language processing: a guide to theory, algorithm, and system development. Upper Saddle River, NJ, USA: Prentice Hall PTR, 1st ed., 2001.","edition":"1"},{"key":"e_1_3_2_1_21_1","first-page":"220","article-title":"Applications of decision tree methodology in speech recognition and understanding","volume":"1","author":"Kuhn R.","year":"1994","unstructured":"R. Kuhn , A. Lazarides , Y. Normandin , J. Brousseau , and E. N\u00f6th , \" Applications of decision tree methodology in speech recognition and understanding ,\" Proceedings in Artificial Intelligence , vol. 1 , pp. 220 -- 232 , 1994 . R. Kuhn, A. Lazarides, Y. Normandin, J. Brousseau, and E. N\u00f6th, \"Applications of decision tree methodology in speech recognition and understanding,\" Proceedings in Artificial Intelligence, vol. 1, pp. 220--232, 1994.","journal-title":"Proceedings in Artificial Intelligence"}],"event":{"name":"ICMLC '19: 2019 11th International Conference on Machine Learning and Computing","sponsor":["Southwest Jiaotong University"],"location":"Zhuhai China","acronym":"ICMLC '19"},"container-title":["Proceedings of the 2019 11th International Conference on Machine Learning and Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3318299.3318385","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3318299.3318385","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:02:24Z","timestamp":1750208544000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3318299.3318385"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,22]]},"references-count":21,"alternative-id":["10.1145\/3318299.3318385","10.1145\/3318299"],"URL":"https:\/\/doi.org\/10.1145\/3318299.3318385","relation":{},"subject":[],"published":{"date-parts":[[2019,2,22]]},"assertion":[{"value":"2019-02-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}