{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T05:34:07Z","timestamp":1772861647923,"version":"3.50.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T00:00:00Z","timestamp":1662940800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T00:00:00Z","timestamp":1662940800000},"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":["Wireless Pers Commun"],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1007\/s11277-022-09829-1","type":"journal-article","created":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T08:02:50Z","timestamp":1662969770000},"page":"2557-2577","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["ERIL: An Algorithm for Emotion Recognition from Indian Languages Using Machine Learning"],"prefix":"10.1007","volume":"126","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2329-2547","authenticated-orcid":false,"given":"Pramod","family":"Mehra","sequence":"first","affiliation":[]},{"given":"Parag","family":"Jain","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,12]]},"reference":[{"key":"9829_CR1","doi-asserted-by":"crossref","unstructured":"Shrawankar, U., & Thakare V. (2010). Feature extraction for a speech recognition system in noisy environment: A study. In: 2010 second international conference on computer engineering and applications (pp. 358\u2013361). Bali, Indonesia.","DOI":"10.1109\/ICCEA.2010.76"},{"key":"9829_CR2","unstructured":"Chaloupka, J., \u010cerva, P., Silovsk\u00fd, J., \u017dd'\u00e1nsk\u00fd, J. & Nouza, J. (2012). Modification of the speech feature extraction module for the improvement of the system for automatic lectures transcription. In: Proceedings ELMAR-2012 (pp. 223\u2013226). Zadar, Croatia."},{"key":"9829_CR3","doi-asserted-by":"crossref","unstructured":"Chadha, A. N., Zaveri, M. A., & Sarvaiya, J. N. (2016). Optimal feature extraction and selection techniques for speech processing: A review. In: International conference on communication and signal processing (ICCSP) (pp. 1669\u20131673). Melmaruvathur, India.","DOI":"10.1109\/ICCSP.2016.7754447"},{"key":"9829_CR4","doi-asserted-by":"crossref","unstructured":"Letaifa, L. B., Torres, M. I., & Justo, R. (2020). Adding dimensional features for emotion recognition on speech. In: 2020 5th international conference on advanced technologies for signal and image processing (ATSIP) (pp. 1\u20136). Sousse, Tunisia.","DOI":"10.1109\/ATSIP49331.2020.9231766"},{"key":"9829_CR5","doi-asserted-by":"crossref","unstructured":"Strengers, Y., & Kennedy, J. (2020). 1 Meet the smart wife. In: The smart wife: Why Siri, Alexa, and other smart home devices need a feminist reboot (pp.1\u201322). MIT Press.","DOI":"10.7551\/mitpress\/12482.001.0001"},{"key":"9829_CR6","doi-asserted-by":"crossref","unstructured":"Lakomkin, E., Zamani, M. A., Weber, C., Magg, S. & Wermter, S. (2019). Incorporating end-to-end speech recognition models for sentiment analysis. In: International conference on robotics and automation (ICRA) (pp. 7976\u20137982). Montreal, QC, Canada.","DOI":"10.1109\/ICRA.2019.8794468"},{"key":"9829_CR7","doi-asserted-by":"crossref","unstructured":"Sajjad, M. & Kwon, S. (2020). Clustering-Based Speech Emotion Recognition by Incorporating Learned Features and Deep BiLSTM. In: IEEE access (Vol. 8, pp. 79861\u201379875).","DOI":"10.1109\/ACCESS.2020.2990405"},{"key":"9829_CR8","doi-asserted-by":"crossref","unstructured":"Garg, K. & Jain, G. (2016) A comparative study of noise reduction techniques for automatic speech recognition systems. In: International conference on advances in computing, communications and informatics (ICACCI) (pp. 2098\u20132103). Jaipur, India.","DOI":"10.1109\/ICACCI.2016.7732361"},{"key":"9829_CR9","doi-asserted-by":"crossref","unstructured":"S\u00e1rosi, G., Mozs\u00e1ry, M., Mihajlik, P., & Fegy\u00f3, T. (2011) Comparison of feature extraction methods for speech recognition in noise-free and in traffic noise environment. In: 6th conference on speech technology and human-computer dialogue (SpeD) (pp. 1\u20138). Brasov, Romania.","DOI":"10.1109\/SPED.2011.5940729"},{"key":"9829_CR10","doi-asserted-by":"publisher","DOI":"10.5772\/intechopen.80419,Dec","author":"SA Alim","year":"2018","unstructured":"Alim, S. A., & Rashid, N. K. A. (2018). Some commonly used speech feature extraction algorithms. From Natural to Artificial Intelligence-Algorithms and Applications. https:\/\/doi.org\/10.5772\/intechopen.80419,Dec","journal-title":"From Natural to Artificial Intelligence-Algorithms and Applications"},{"issue":"10","key":"9829_CR11","first-page":"18551","volume":"5","author":"AS Gill","year":"2016","unstructured":"Gill, A. S. (2016). A review on feature extraction techniques for speech processing. International Journal of Engineering and Computer Science, 5(10), 18551\u201318556.","journal-title":"International Journal of Engineering and Computer Science"},{"issue":"S1","key":"9829_CR12","doi-asserted-by":"publisher","first-page":"S35","DOI":"10.1121\/1.1995189","volume":"57","author":"F Itakura","year":"1975","unstructured":"Itakura, F. (1975). Line spectrum representation of linear predictor coefficients of speech signals. The Journal of the Acoustical Society of America., 57(S1), S35\u2013S35.","journal-title":"The Journal of the Acoustical Society of America."},{"issue":"4","key":"9829_CR13","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/s12046-018-0841-y","volume":"43","author":"B Aarti","year":"2018","unstructured":"Aarti, B., & Kopparapu, S. K. (2018). Spoken Indian language identification: A review of features and databases. S\u0101dhan\u0101, 43(4), 53. https:\/\/doi.org\/10.1007\/s12046-018-0841-y","journal-title":"S\u0101dhan\u0101"},{"key":"9829_CR14","doi-asserted-by":"publisher","first-page":"46007","DOI":"10.1109\/ACCESS.2020.2978163","volume":"8","author":"Y Luo","year":"2020","unstructured":"Luo, Y., et al. (2020). EEG-based emotion classification using spiking neural networks. IEEE Access, 8, 46007\u201346016. https:\/\/doi.org\/10.1109\/ACCESS.2020.2978163","journal-title":"IEEE Access"},{"key":"9829_CR15","doi-asserted-by":"crossref","unstructured":"Mohammad Amini, M., & Matrouf, D. (2021). Data augmentation versus noise compensation for x-vector speaker recognition systems in noisy environments. In: 28th European signal processing conference (EUSIPCO) (pp. 1\u20135). Amsterdam, Netherlands.","DOI":"10.23919\/Eusipco47968.2020.9287690"},{"issue":"16","key":"9829_CR16","doi-asserted-by":"publisher","first-page":"3396","DOI":"10.3390\/app9163396","volume":"9","author":"J Wu","year":"2019","unstructured":"Wu, J., Hua, Y., Yang, S., Qin, H., & Qin, H. (2019). Speech enhancement using generative adversarial network by distilling knowledge from statistical method. Applied Sciences, 9(16), 3396. https:\/\/doi.org\/10.3390\/app9163396","journal-title":"Applied Sciences"},{"key":"9829_CR17","doi-asserted-by":"crossref","unstructured":"Cummins, N., Amiriparian, S., Hagerer, G., Batliner, A., Steidl, S., & Schuller, B. W. (2017). An image-based deep spectrum feature representation for the recognition of emotional speech. In: Proceedings of the 25th ACM multimedia conference (MM) (pp. 478\u2013484).","DOI":"10.1145\/3123266.3123371"},{"key":"9829_CR18","doi-asserted-by":"publisher","first-page":"67718","DOI":"10.1109\/ACCESS.2019.2916828","volume":"7","author":"F Karim","year":"2019","unstructured":"Karim, F., Majumdar, S., & Darabi, H. (2019). Insights into LSTM fully convolutional networks for time series classification. IEEE Access, 7, 67718\u201367725.","journal-title":"IEEE Access"},{"issue":"10","key":"9829_CR19","doi-asserted-by":"publisher","first-page":"1702","DOI":"10.1109\/TASLP.2018.2842159,Oct","volume":"26","author":"D Wang","year":"2018","unstructured":"Wang, D., & Chen, J. (2018). Supervised speech separation based on deep learning: An overview. IEEE\/ACM Transactions Audio, Speech, and Language Processing, 26(10), 1702\u20131726. https:\/\/doi.org\/10.1109\/TASLP.2018.2842159,Oct","journal-title":"IEEE\/ACM Transactions Audio, Speech, and Language Processing"},{"key":"9829_CR20","doi-asserted-by":"crossref","unstructured":"Pulugundla, B. et al. (2018). BUT system for low resource Indian Language ASR. In: Interspeech (pp. 3182\u20133186).","DOI":"10.21437\/Interspeech.2018-1302"},{"key":"9829_CR21","doi-asserted-by":"crossref","unstructured":"Gogoi, S., & Bhattacharjee, U. (2017). Vocal tract length normalization and sub-band spectral subtraction based robust Assamese vowel recognition system. In: International conference on computing methodologies and communication (ICCMC) (pp. 32\u201335). Erode.","DOI":"10.1109\/ICCMC.2017.8282709"},{"issue":"3","key":"9829_CR22","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/s00530-015-0499-9,Jun","volume":"22","author":"J Wang","year":"2016","unstructured":"Wang, J., Zhang, J., Honda, K., Wei, J., & Dang, J. (2016). Audio-visual speech recognition integrating 3D lip information obtained from the Kinect. Multimedia Systems, 22(3), 315\u2013323. https:\/\/doi.org\/10.1007\/s00530-015-0499-9,Jun","journal-title":"Multimedia Systems"},{"issue":"6","key":"9829_CR23","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1016\/j.wocn.2013.07.004","volume":"41","author":"H Sirsa","year":"2013","unstructured":"Sirsa, H., & Redford, M. A. (2013). The effects of native language on Indian English sounds and timing patterns. Journal of Phonetics, 41(6), 393\u2013406. https:\/\/doi.org\/10.1016\/j.wocn.2013.07.004","journal-title":"Journal of Phonetics"},{"key":"9829_CR24","doi-asserted-by":"crossref","unstructured":"Singh, J., & Kaur, K. (2019). Speech enhancement for Punjabi Language using deep neural network. In: International conference on signal processing and communication (ICSC) (pp. 202\u2013204). Noida, India.","DOI":"10.1109\/ICSC45622.2019.8938309"},{"key":"9829_CR25","doi-asserted-by":"crossref","unstructured":"Reddy, M. G., et al. (2015). Automatic pitch accent contour transcription for Indian languages. In: International conference on computer, communication and control (IC4) (pp. 1\u20136). Indore, India.","DOI":"10.1109\/IC4.2015.7375669"},{"issue":"1","key":"9829_CR26","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1007\/s10772-015-9326-0","volume":"19","author":"PK Polasi","year":"2016","unstructured":"Polasi, P. K., Krishna, S. R., & K. (2016). Combining the evidences of temporal and spectral enhancement techniques for improving the performance of Indian language identification system in the presence of background noise. International Journal of Speech Technology, 19(1), 75\u201385. https:\/\/doi.org\/10.1007\/s10772-015-9326-0","journal-title":"International Journal of Speech Technology"},{"issue":"8","key":"9829_CR27","doi-asserted-by":"publisher","first-page":"1731","DOI":"10.1080\/02522667.2019.1703266","volume":"40","author":"A Patil","year":"2019","unstructured":"Patil, A., More, P., & Sasikumar, M. (2019). Incorporating finer acoustic phonetic features in lexicon for Hindi language speech recognition. Journal of Information and Optimization Sciences, 40(8), 1731\u20131739. https:\/\/doi.org\/10.1080\/02522667.2019.1703266","journal-title":"Journal of Information and Optimization Sciences"},{"key":"9829_CR28","unstructured":"Nath, S., Chakraborty, J., & Sarmah, P. (2018). Machine identification of spoken Indian languages. pp. 6."},{"key":"9829_CR29","doi-asserted-by":"crossref","unstructured":"Mullah, H. U., Pyrtuh, F., & Singh, L. J. (2015). Development of an HMM-based speech synthesis system for Indian English language. In: 2015 international symposium on advanced computing and communication (ISACC) (pp. 124\u2013127). Silchar, India.","DOI":"10.1109\/ISACC.2015.7377327"},{"key":"9829_CR30","doi-asserted-by":"crossref","unstructured":"Londhe, N. D., Ahirwal, M. K., & Lodha, P. (2016). Machine learning paradigms for speech recognition of an Indian dialect. In International conference on communication and signal processing (ICCSP), (pp. 0780\u20130786). Melmaruvathur, Tamilnadu, India.","DOI":"10.1109\/ICCSP.2016.7754251"},{"issue":"1","key":"9829_CR31","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/s00530-006-0034-0","volume":"12","author":"MKS Khan","year":"2006","unstructured":"Khan, M. K. S., & Al-Khatib, W. G. (2006). Machine-learning based classification of speech and music. Multimedia Systems, 12(1), 55\u201367. https:\/\/doi.org\/10.1007\/s00530-006-0034-0","journal-title":"Multimedia Systems"},{"key":"9829_CR32","doi-asserted-by":"crossref","unstructured":"Hao, X., Wen, S., Su, X., Liu, Y., Gao, G., & Li, X. (2020). Sub-band knowledge distillation framework for speech enhancement. In: Interspeech (pp. 2687\u20132691).","DOI":"10.21437\/Interspeech.2020-1539"},{"key":"9829_CR33","doi-asserted-by":"crossref","unstructured":"Yang C., Xie L., Su C., & Yuille A. L. (2019). Snapshot distillation: Teacher-student optimization in one generation. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2854\u20132863).","DOI":"10.1109\/CVPR.2019.00297"},{"key":"9829_CR34","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1016\/j.procs.2016.07.259","volume":"93","author":"A Desai Vijayendra","year":"2016","unstructured":"Desai Vijayendra, A., & Thakar, V. K. (2016). Neural network based Gujarati speech recognition for dataset collected by in-ear microphone. Procedia Computer Science, 93, 668\u2013675. https:\/\/doi.org\/10.1016\/j.procs.2016.07.259","journal-title":"Procedia Computer Science"},{"key":"9829_CR35","first-page":"3207","volume":"2018","author":"J Billa","year":"2018","unstructured":"Billa, J. (2018). ISI ASR system for the low resource speech recognition challenge for Indian languages. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 2018, 3207\u20133211.","journal-title":"Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH"},{"key":"9829_CR36","doi-asserted-by":"crossref","unstructured":"Fang, M., Zhao, H., Song, X., Wang, X., & Huang, S. (2019). Using bidirectional LSTM with BERT for Chinese punctuation prediction. In: IEEE International Conference on Signal, Information and Data Processing (ICSIDP) (pp. 1\u20135). Chongqing, China.","DOI":"10.1109\/ICSIDP47821.2019.9172986"},{"key":"9829_CR37","doi-asserted-by":"crossref","unstructured":"Kierszbaum, S., & Lapasset, L. (2020). Applying distilled BERT for question answering on ASRS reports. In: New trends in civil aviation (NTCA) (pp. 33\u201338). Prague, Czech Republic.","DOI":"10.23919\/NTCA50409.2020.9291241"},{"key":"9829_CR38","unstructured":"Luo, S. -B., Kuo, C. -C., & Chen, K. -Y. (2020). Spoken multiple-choice question answering using multi-turn audio-extractor BERT. In: 2020 Asia-Pacific signal and information processing association annual summit and conference (APSIPA ASC) (pp. 386\u2013392). Auckland, New Zealand."},{"key":"9829_CR39","doi-asserted-by":"publisher","first-page":"79861","DOI":"10.1109\/ACCESS.2020.2990405","volume":"8","author":"M Sajjad","year":"2020","unstructured":"Sajjad, M., & Kwon, S. (2020). Clustering-based speech emotion recognition by incorporating learned features and deep BiLSTM. IEEE Access, 8, 79861\u201379875. https:\/\/doi.org\/10.1109\/ACCESS.2020.2990405","journal-title":"IEEE Access"},{"issue":"1","key":"9829_CR40","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1007\/s10772-015-9326-0","volume":"19","author":"PK Polasi","year":"2016","unstructured":"Polasi, P. K., & Sri RamaKrishna, K. (2016). Combining the evidences of temporal and spectral enhancement techniques for improving the performance of Indian language identification system in the presence of background noise. International Journal of Speech Technology, 19(1), 75\u201385. https:\/\/doi.org\/10.1007\/s10772-015-9326-0","journal-title":"International Journal of Speech Technology"},{"key":"9829_CR41","doi-asserted-by":"publisher","first-page":"181432","DOI":"10.1109\/ACCESS.2020.3028241","volume":"8","author":"A Das","year":"2020","unstructured":"Das, A., Guha, S., Singh, P. K., Ahmadian, A., Senu, N., & Sarkar, R. (2020). A hybrid meta-heuristic feature selection method for identification of Indian spoken languages from audio signals. IEEE Access, 8, 181432\u2013181449. https:\/\/doi.org\/10.1109\/ACCESS.2020.3028241","journal-title":"IEEE Access"},{"key":"9829_CR42","doi-asserted-by":"crossref","unstructured":"Mullah, H. U., Pyrtuh, F., & Singh, L. J. (2015). Development of an HMM-based speech synthesis system for Indian English language. In: International symposium on advanced computing and communication (ISACC) (pp. 124\u2013127). Silchar, India.","DOI":"10.1109\/ISACC.2015.7377327"},{"key":"9829_CR43","doi-asserted-by":"crossref","unstructured":"Bharti, D., & Kukana, P. (2020). A hybrid machine learning model for emotion recognition from speech signals. In: 2020 international conference on smart electronics and communication (ICOSEC) (pp. 491\u2013496).","DOI":"10.1109\/ICOSEC49089.2020.9215376"},{"issue":"2","key":"9829_CR44","doi-asserted-by":"publisher","first-page":"22","DOI":"10.5120\/ijca2015905837","volume":"125","author":"RP Gadhe","year":"2015","unstructured":"Gadhe, R. P., Babasaheb, D., Deshmukh, R. R., & Babasaheb, D. (2015). Emotion recognition from isolated Marathi speech using energy and formants. International Journal of Computer Applications., 125(2), 22\u201324.","journal-title":"International Journal of Computer Applications."},{"key":"9829_CR45","doi-asserted-by":"crossref","unstructured":"Sowmya, V. & Rajeswari, A. (2020). Speech emotion recognition for Tamil language speakers (pp. 125\u2013136).","DOI":"10.1007\/978-981-15-1366-4_10"},{"key":"9829_CR46","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1016\/j.protcy.2016.05.242","volume":"24","author":"TM Rajisha","year":"2016","unstructured":"Rajisha, T. M., Prabhakaran, S., & Riyas, K. S. (2016). Performance analysis of Malayalam language speech emotion recognition system using ANN\/SVM. Procedia Technology, 24, 1097\u20131104. https:\/\/doi.org\/10.1016\/j.protcy.2016.05.242","journal-title":"Procedia Technology"},{"key":"9829_CR47","doi-asserted-by":"publisher","unstructured":"Chandran, A., Pravena, D., & Govind, D. (2017). Development of speech emotion recognition system using deep belief networks in Malayalam language. In: International conference on advances in computing, communications and informatics (ICACCI) (pp. 676\u2013680). https:\/\/doi.org\/10.1109\/ICACCI.2017.8125919","DOI":"10.1109\/ICACCI.2017.8125919"}],"container-title":["Wireless Personal Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-022-09829-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11277-022-09829-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-022-09829-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,12]],"date-time":"2022-10-12T16:31:43Z","timestamp":1665592303000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11277-022-09829-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,12]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["9829"],"URL":"https:\/\/doi.org\/10.1007\/s11277-022-09829-1","relation":{},"ISSN":["0929-6212","1572-834X"],"issn-type":[{"value":"0929-6212","type":"print"},{"value":"1572-834X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,12]]},"assertion":[{"value":"28 May 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 September 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}