{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:23:56Z","timestamp":1740122636313,"version":"3.37.3"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,2,10]],"date-time":"2022-02-10T00:00:00Z","timestamp":1644451200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,2,10]],"date-time":"2022-02-10T00:00:00Z","timestamp":1644451200000},"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":[[2022,7]]},"DOI":"10.1007\/s11277-022-09549-6","type":"journal-article","created":{"date-parts":[[2022,2,10]],"date-time":"2022-02-10T07:03:44Z","timestamp":1644476624000},"page":"261-280","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["G-Cocktail: An Algorithm to Address Cocktail Party Problem of Gujarati Language Using Cat Boost"],"prefix":"10.1007","volume":"125","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2788-5462","authenticated-orcid":false,"given":"Monika","family":"Gupta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R. K.","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sachin","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,2,10]]},"reference":[{"issue":"5","key":"9549_CR1","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1007\/s12046-011-0039-z,Oct","volume":"36","author":"P Bhaskararao","year":"2011","unstructured":"Bhaskararao, P. (2011). Salient phonetic features of Indian languages in speech technology. Sadhana, 36(5), 587\u2013599. https:\/\/doi.org\/10.1007\/s12046-011-0039-z,Oct","journal-title":"Sadhana"},{"key":"9549_CR2","doi-asserted-by":"publisher","first-page":"78421","DOI":"10.1109\/ACCESS.2019.2922370","volume":"7","author":"GS Bhat","year":"2019","unstructured":"Bhat, G. S., Shankar, N., Reddy, C. K. A., & Panahi, I. M. S. (2019). A real-time convolutional neural network based speech enhancement for hearing impaired listeners using smartphone. IEEE Access, 7, 78421\u201378433. https:\/\/doi.org\/10.1109\/ACCESS.2019.2922370","journal-title":"IEEE Access"},{"key":"9549_CR3","doi-asserted-by":"publisher","unstructured":"Yarra, C., Aggarwal, R., Rajpal, A., & Ghosh, P. K. (2019). Indic TIMIT and Indic English lexicon: A speech database of Indian speakers using TIMIT stimuli and a lexicon from their mispronunciations. In: 2019 22nd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardization of Speech Databases and Assessment Techniques (O-COCOSDA), Cebu, Philippines, pp. 1\u20136, doi: https:\/\/doi.org\/10.1109\/O-COCOSDA46868.2019.9041230.","DOI":"10.1109\/O-COCOSDA46868.2019.9041230"},{"issue":"5","key":"9549_CR4","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1049\/iet-spr.2019.0226,Jul","volume":"14","author":"MPA Jeeva","year":"2020","unstructured":"Jeeva, M. P. A., Nagarajan, T., & Vijayalakshmi, P. (2020). Adaptive multi-band filter structure-based far-end speech enhancement. IET Signal Process, 14(5), 288\u2013299. https:\/\/doi.org\/10.1049\/iet-spr.2019.0226,Jul","journal-title":"IET Signal Process"},{"issue":"4","key":"9549_CR5","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1007\/s00530-020-00659-4","volume":"26","author":"SP Panda","year":"2020","unstructured":"Panda, S. P., Nayak, A. K., & Rai, S. C. (2020). A survey on speech synthesis techniques in Indian languages. Multimedia Systems, 26(4), 453\u2013478. https:\/\/doi.org\/10.1007\/s00530-020-00659-4","journal-title":"Multimedia Systems"},{"key":"9549_CR6","doi-asserted-by":"publisher","unstructured":"Sarkar, P., Haque, A., Dutta, A. K., Gurunath Reddy, M., Harikrishna D. M., Dhara, P., Rashmi, V., Narendra, N. P., Sunil Kr. S. B., Yadav, J., & Sreenivasa Rao, K. (2014). Designing prosody rule-set for converting neutral TTS speech to storytelling style speech for Indian languages: Bengali, Hindi and Telugu,\u201d in Seventh International Conference on Contemporary Computing (IC3), Noida,, pp. 473\u2013477,doi: https:\/\/doi.org\/10.1109\/IC3.2014.6897219.","DOI":"10.1109\/IC3.2014.6897219"},{"key":"9549_CR7","unstructured":"Mishra, N., Tech, M., Shrawankar, U., & Thakare, D. V. M. (2010). AN OVERVIEW OF HINDI SPEECH RECOGNITION. In: Proceedings of the International Conference on Computational Systems and Communication Technology -Tamil Nadu, p. 6, May 5 2010."},{"issue":"5","key":"9549_CR8","doi-asserted-by":"publisher","first-page":"17","DOI":"10.5120\/7184-9893","volume":"47","author":"PP Shri Shrimal","year":"2012","unstructured":"Shri Shrimal, P. P., Deshmukh, R. R., & Waghmare, V. B. (2012). Indian language speech database: A review. IJCA, 47(5), 17\u201321. https:\/\/doi.org\/10.5120\/7184-9893","journal-title":"IJCA"},{"issue":"6","key":"9549_CR9","doi-asserted-by":"publisher","first-page":"780","DOI":"10.1016\/j.wocn.2012.07.001","volume":"40","author":"SD ud Khan","year":"2012","unstructured":"ud Khan, S. D. (2012). The phonetics of contrastive phonation in Gujarati. Journal of Phonetics, 40(6), 780\u2013795. https:\/\/doi.org\/10.1016\/j.wocn.2012.07.001","journal-title":"Journal of Phonetics"},{"issue":"10","key":"9549_CR10","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 on Audio, Speech, and Language Processing, 26(10), 1702\u20131726. https:\/\/doi.org\/10.1109\/TASLP.2018.2842159,Oct","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"3","key":"9549_CR11","doi-asserted-by":"publisher","first-page":"53","DOI":"10.5865\/IJKCT.2018.8.3.053,Sep","volume":"8","author":"BK Roy","year":"2018","unstructured":"Roy, B. K., Biswas, S. C., & Mukhopadhyay, P. (2018). Designing unicode-compliant Indic-script based institutional digital repository with special reference to Bengali. International Journal of Knowledge Content Development & Technology, 8(3), 53\u201367. https:\/\/doi.org\/10.5865\/IJKCT.2018.8.3.053,Sep","journal-title":"International Journal of Knowledge Content Development & Technology"},{"key":"9549_CR12","unstructured":"Sproat, R., (2003). A formal computational analysis of indic scripts. In: International Symposium on Indic Scripts: Past and Future, Tokyo, Dec. 2003."},{"key":"9549_CR13","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1016\/j.procs.2015.06.066","volume":"54","author":"N Upadhyay","year":"2015","unstructured":"Upadhyay, N., & Karmakar, A. (2015). Speech enhancement using spectral subtraction-type algorithms: A comparison and simulation study. Procedia Computer Science, 54, 574\u2013584. https:\/\/doi.org\/10.1016\/j.procs.2015.06.066","journal-title":"Procedia Computer Science"},{"key":"9549_CR14","doi-asserted-by":"publisher","unstructured":"Upadhyay, N. (2014). An improved multi-band speech enhancement utilizing masking properties of human hearing system. In: 2014 Fifth International Symposium on Electronic System Design, Surathkal, Mangalore, India, pp. 150\u2013155, doi: https:\/\/doi.org\/10.1109\/ISED.2014.38.","DOI":"10.1109\/ISED.2014.38"},{"issue":"2","key":"9549_CR15","doi-asserted-by":"publisher","first-page":"754","DOI":"10.1109\/TVLSI.2015.2413454","volume":"24","author":"J Jo","year":"2016","unstructured":"Jo, J., Yoo, H., & Park, I. (2016). Energy-efficient floating-point MFCC extraction architecture for speech recognition systems. IEEE Transactions on Very Large-Scale Integration (VLSI) Systems, 24(2), 754\u2013758.","journal-title":"IEEE Transactions on Very Large-Scale Integration (VLSI) Systems"},{"key":"9549_CR16","doi-asserted-by":"publisher","unstructured":"Chakroborty, S., Roy, A., & Saha, G. (2006). Fusion of a complementary feature set with MFCC for improved closed set text-independent speaker identification. In: 2006 IEEE International Conference on Industrial Technology, Mumbai, India, pp. 387\u2013390, doi: https:\/\/doi.org\/10.1109\/ICIT.2006.372388.","DOI":"10.1109\/ICIT.2006.372388"},{"key":"9549_CR17","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":"9549_CR18","doi-asserted-by":"publisher","unstructured":"Garg, K., & Jain, G. (2016). A comparative study of noise reduction techniques for automatic speech recognition systems. In: 2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI), Jaipur, India, pp. 2098\u20132103, doi: https:\/\/doi.org\/10.1109\/ICACCI.2016.7732361","DOI":"10.1109\/ICACCI.2016.7732361"},{"key":"9549_CR19","doi-asserted-by":"publisher","DOI":"10.5772\/intechopen.80419","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","journal-title":"From Natural to Artificial Intelligence - Algorithms and Applications"},{"issue":"1","key":"9549_CR20","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/1687-4722-2012-7","volume":"2012","author":"NS Nehe","year":"2012","unstructured":"Nehe, N. S., & Holambe, R. S. (2012). DWT and LPC based feature extraction methods for isolated word recognition. EURASIP Journal on Audio, Speech, and Music Processing, 2012(1), 7. https:\/\/doi.org\/10.1186\/1687-4722-2012-7","journal-title":"EURASIP Journal on Audio, Speech, and Music Processing"},{"issue":"9","key":"9549_CR21","doi-asserted-by":"publisher","first-page":"806","DOI":"10.1109\/LSP.2009.2024113","volume":"16","author":"J Hung","year":"2009","unstructured":"Hung, J., & Fan, H. (2009). Subband feature statistics normalization techniques based on a discrete wavelet transform for robust speech recognition. IEEE Signal Processing Letters, 16(9), 806\u2013809. https:\/\/doi.org\/10.1109\/LSP.2009.2024113","journal-title":"IEEE Signal Processing Letters"},{"key":"9549_CR22","doi-asserted-by":"publisher","unstructured":"Eltiraifi, O., Elbasheer, E., & Nawari, M. (2018). A comparative study of MFCC and LPCC features for speech activity detection using deep belief network. In: 2018 International Conference on Computer, Control, Electrical, and Electronics Engineering (ICCCEEE), Khartoum, pp. 1\u20135, doi: https:\/\/doi.org\/10.1109\/ICCCEEE.2018.8515821","DOI":"10.1109\/ICCCEEE.2018.8515821"},{"key":"9549_CR23","doi-asserted-by":"publisher","unstructured":"Dehak, N., Torres-Carrasquillo, P., Reynolds, D., & Dehak, R, (2011). Language recognition via I-vectors and dimensionality reduction. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp 857\u2013860. https:\/\/doi.org\/10.21437\/Interspeech.2011-328.","DOI":"10.21437\/Interspeech.2011-328"},{"key":"9549_CR24","doi-asserted-by":"publisher","unstructured":"Mohammad Amini, M., & Matrouf, D. (2021). Data augmentation versus noise compensation for x-vector speaker recognition systems in noisy environments,\" 2020 28th European Signal Processing Conference (EUSIPCO), Amsterdam, Netherlands, pp. 1\u20135, doi: https:\/\/doi.org\/10.23919\/Eusipco47968.2020.9287690","DOI":"10.23919\/Eusipco47968.2020.9287690"},{"issue":"16","key":"9549_CR25","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":"9549_CR26","doi-asserted-by":"publisher","first-page":"3182","DOI":"10.21437\/Interspeech.2018-1302","volume":"2018","author":"B Pulugundla","year":"2018","unstructured":"Pulugundla, B., Karthick, M., Kesiraju, S., & Kgorova, K. (2018). BUT system for low resource Indian language ASR. Interspeech, 2018, 3182\u20133186. https:\/\/doi.org\/10.21437\/Interspeech.2018-1302","journal-title":"Interspeech"},{"key":"9549_CR27","doi-asserted-by":"publisher","unstructured":"Gogoi, S., & Bhattacharjee, U., (2017). Vocal tract length normalization and sub-band spectral subtraction based robust assamese vowel recognition system. In: 2017 International Conference on Computing Methodologies and Communication (ICCMC), Erode, pp. 32\u201335, doi: https:\/\/doi.org\/10.1109\/ICCMC.2017.8282709","DOI":"10.1109\/ICCMC.2017.8282709"},{"issue":"3","key":"9549_CR28","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/s00530-015-0499-9","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","journal-title":"Multimedia Systems"},{"key":"9549_CR29","volume-title":"Characteristics of Indian Languages","author":"M Varalwar","year":"2006","unstructured":"Varalwar, M., & Patel, N. (2006). Characteristics of Indian Languages. Bhrigus Inc."},{"issue":"6","key":"9549_CR30","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":"9549_CR31","doi-asserted-by":"publisher","unstructured":"Singh, J. & Kaur, K. (2019). Speech eEnhancement for Punjabi language using deep neural network. In: 2019 International Conference on Signal Processing and Communication (ICSC), NOIDA, India, pp. 202\u2013204, doi: https:\/\/doi.org\/10.1109\/ICSC45622.2019.8938309.","DOI":"10.1109\/ICSC45622.2019.8938309"},{"key":"9549_CR32","doi-asserted-by":"publisher","unstructured":"Reddy, M. G., Sen, Manjunath, K., Sarkar, P., & Rao, K. S. (2015). Automatic pitch accent contour transcription for Indian languages. In: 2015 International Conference on Computer, Communication and Control (IC4), Indore, India, pp. 1\u20136, doi: https:\/\/doi.org\/10.1109\/IC4.2015.7375669.","DOI":"10.1109\/IC4.2015.7375669"},{"issue":"1","key":"9549_CR33","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 Rama Krishna, 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":"9549_CR34","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":"9549_CR35","unstructured":"Parikh, R. B., & Joshi, D. H. (2020). Gujarati speech recognition \u2013 A review. No. 549, p. 6."},{"key":"9549_CR36","unstructured":"Nath, S., Chakraborty, J., Sarmah, P. (2018) Machine identification of spoken Indian languages,\u201d p. 6."},{"key":"9549_CR37","doi-asserted-by":"publisher","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), Silchar, India, pp. 124\u2013127, doi: https:\/\/doi.org\/10.1109\/ISACC.2015.7377327, 2015.","DOI":"10.1109\/ISACC.2015.7377327"},{"key":"9549_CR38","doi-asserted-by":"publisher","unstructured":"Morris, A., Maier, V., Green, P. (2004). From WER and RIL to MER and WIL: Improved evaluation measures for connected speech recognition, https:\/\/doi.org\/10.21437\/Interspeech.2004-668.","DOI":"10.21437\/Interspeech.2004-668"},{"key":"9549_CR39","doi-asserted-by":"publisher","unstructured":"Londhe, N. D., Ahirwal, M. K., & Lodha, P. (2016). Machine learning paradigms for speech recognition of an Indian dialect. In: 2016 International Conference on Communication and Signal Processing (ICCSP), Melmaruvathur, Tamilnadu, India, pp. 0780\u20130786, doi: https:\/\/doi.org\/10.1109\/ICCSP.2016.7754251.","DOI":"10.1109\/ICCSP.2016.7754251"},{"key":"9549_CR40","doi-asserted-by":"publisher","first-page":"48720","DOI":"10.1109\/ACCESS.2020.2979799","volume":"8","author":"Q Li","year":"2020","unstructured":"Li, Q., Yang, Y., Lan, F., Zhu, H., Wei, Q., Qia, F., Liu, Z., & Yang, H. (2020). MSP-MFCC: Energy-efficient MFCC feature extraction method with mixed-signal processing architecture for wearable speech recognition applications. IEEE Access, 8, 48720\u201348730. https:\/\/doi.org\/10.1109\/ACCESS.2020.2979799","journal-title":"IEEE Access"},{"key":"9549_CR41","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1109\/TASLP.2020.2986877","volume":"28","author":"T Lavanya","year":"2020","unstructured":"Lavanya, T., Nagarajan, T., & Vijayalakshmi, P. (2020). Multi-level single-channel speech enhancement using a unified framework for estimating magnitude and phase spectra. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 28, 1315\u20131327. https:\/\/doi.org\/10.1109\/TASLP.2020.2986877","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"9549_CR42","doi-asserted-by":"publisher","unstructured":"S. Kiruthiga and K. Krishnamoorthy, \u201cDesign issues in developing speech corpus for Indian languages — A survey. In: 2012 International Conference on Computer Communication and Informatics, Coimbatore, India, pp. 1\u20134, doi: https:\/\/doi.org\/10.1109\/ICCCI.2012.6158831.","DOI":"10.1109\/ICCCI.2012.6158831"},{"issue":"1","key":"9549_CR43","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":"9549_CR44","unstructured":"Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.- Y. (2017). Light GBM: A highly efficient gradient boosting decision tree. In: 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, p. 9, 2017."},{"key":"9549_CR45","doi-asserted-by":"publisher","unstructured":"Joshi, M., Iyer, M., & Gupta, N. (2010). Effect of accent on speech intelligibility in multiple speaker environment with sound spatialization. In: 2010 Seventh International Conference on Information Technology: New Generations, Las Vegas, NV, USA, pp. 338\u2013342, doi: https:\/\/doi.org\/10.1109\/ITNG.2010.11.","DOI":"10.1109\/ITNG.2010.11"},{"key":"9549_CR46","doi-asserted-by":"publisher","first-page":"2687","DOI":"10.21437\/Interspeech.2020-1539","volume":"2020","author":"X Hao","year":"2020","unstructured":"Hao, X., Wen, S., Su, X., Liu, Y., Gao, G., & Li, X. (2020). Sub-band knowledge distillation framework for speech enhancement. Interspeech, 2020, 2687\u20132691. https:\/\/doi.org\/10.21437\/Interspeech.2020-1539","journal-title":"Interspeech"},{"key":"9549_CR47","doi-asserted-by":"crossref","unstructured":"Yang, C., Xie, L., Su, C., &Yuille, A. L, (2019). Snapshot distillation: Teacher-student optimization in one generation. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2854\u20132863.","DOI":"10.1109\/CVPR.2019.00297"},{"key":"9549_CR48","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":"9549_CR49","unstructured":"Patel, H. N., & Virparia, P. V. (2011) A small vocabulary speech recognition for Gujarati. vol. 2, no. 1."},{"issue":"9","key":"9549_CR50","first-page":"6442","volume":"3297","author":"DS Pipaliahoomikaave","year":"2015","unstructured":"Pipaliahoomikaave, D. S. (2015). An approach to increase word recognition accuracy in Gujarati language. International Journal of Innovative Research in Computer and Communication Engineering, 3297(9), 6442\u20136450.","journal-title":"International Journal of Innovative Research in Computer and Communication Engineering"},{"issue":"12","key":"9549_CR51","doi-asserted-by":"publisher","first-page":"28","DOI":"10.5120\/ijca2016909049","volume":"138","author":"H Jinal","year":"2016","unstructured":"Jinal, H., & Dipti, B. (2016). Speech recognition system architecture for Gujarati language. International Journal of Computer Applications, 138(12), 28\u201331.","journal-title":"International Journal of Computer Applications"},{"key":"9549_CR52","doi-asserted-by":"crossref","unstructured":"Valaki, S., & Jethva, H. (2017). A hybrid HMM\/ANN approach for automatic Gujarati speech recognition. Proc. 2017 Int. Conf. Innov. Information, Embed. Commun. Syst. ICIIECS 2017, vol. 2018-Janua, pp. 1\u20135","DOI":"10.1109\/ICIIECS.2017.8276141"},{"key":"9549_CR53","doi-asserted-by":"crossref","unstructured":"Tailor, J. H., & Shah, D. B. (2017). HMM-based lightweight speech recognition system for Gujarati language. pp. 451\u2013461.","DOI":"10.1007\/978-981-10-3920-1_46"},{"key":"9549_CR54","unstructured":"Sainath, T. N., Weiss, R. J., Li, B., Moreno, P., Weinstein, E., & Rao, K. (2018). Multilingual speech recognition with a single end-to-end model Shubham Toshniwal\u2217 Toyota Technological Institute at Chicago, ICASSP, IEEE Int. Conf. Acoust. Speech Signal Process. - Proc., pp. 4904\u20134908, 2018."},{"key":"9549_CR55","doi-asserted-by":"crossref","unstructured":"Vydana, H. K., Gurugubelli, K., Raju, V. V. V., Vuppala, A. K. (2018). An exploration towards joint acoustic modeling for Indian languages: IIIT-H submission for Low Resource Speech Recognition Challenge for Indian languages, INTERSPEECH 2018,\u201d Proc. Annu. Conf. Int. Speech Commun. Assoc. INTERSPEECH, vol. 2018-Septe, no. September, pp. 3192\u20133196, 2018.","DOI":"10.21437\/Interspeech.2018-1584"},{"key":"9549_CR56","doi-asserted-by":"crossref","unstructured":"Sailor, H. B., Siva Krishna, M. V., Chhabra, D., Patil, A. T., Kamble, M. R., & Patil, H. A. (2018). DA-IICT\/IIITV system for low resource speech recognition challenge 2018. Proc. Annu. Conf. Int. Speech Commun. Assoc. INTERSPEECH, vol. 2018-Septe, no. September, pp. 3187\u20133191, 2018.","DOI":"10.21437\/Interspeech.2018-1553"},{"key":"9549_CR57","doi-asserted-by":"crossref","unstructured":"Billa, J. (2018). ISI ASR system for the low resource speech recognition challenge for Indian languages,\u201d Proc. Annu. Conf. Int. Speech Commun. Assoc. INTERSPEECH, vol. 2018-Septe, no. September, pp. 3207\u20133211, 2018","DOI":"10.21437\/Interspeech.2018-2473"},{"key":"9549_CR58","unstructured":"Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., & Gulin, A. (2021). CatBoost: Unbiased boosting with categorical features,\u201d arXiv:1706.09516 [cs], Jan. 2019, Accessed: Mar. 03, 2021. [Online]. Available https:\/\/arxiv.org\/abs\/1706.09516."},{"key":"9549_CR59","doi-asserted-by":"publisher","unstructured":"Padmapriya. J., Sasilatha, T., Karthickmano, J. R., Aagash, G., & Bharathi, V. (2021). Voice extraction from background noise using filter bank analysis for voice communication applications. In: 2021 Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), 2021, pp. 269\u2013273, doi: https:\/\/doi.org\/10.1109\/ICICV50876.2021.9388453.","DOI":"10.1109\/ICICV50876.2021.9388453"},{"key":"9549_CR60","doi-asserted-by":"crossref","unstructured":"Choudhary, N. (2021). LDC-IL: The Indian repository of resources for language technology.\u00a0Language Resources and Evaluation, pp 1\u201313. https:\/\/www.ldcil.org\/publications.aspx.","DOI":"10.1007\/s10579-020-09523-3"},{"key":"9549_CR61","unstructured":"Bahmaninezhad, F., Wu, J., Gu, R., Zhang, S. -X., Xu, Y., Yu, M., & Yu, D. (2021). A comprehensive study of speech separation: spectrogram vs waveform separation,\u201d arXiv:1905.07497 [cs, eess], p. 2, May 2019, Accessed: Nov. 11, 2021. [Online]. Available: https:\/\/arxiv.org\/abs\/1905.07497."},{"key":"9549_CR62","doi-asserted-by":"publisher","DOI":"10.1016\/j.heares.2021.108294","volume":"408","author":"T Fischer","year":"2021","unstructured":"Fischer, T., Caversaccio, M., & Wimmer, W. (2021). Speech signal enhancement in cocktail party scenarios by deep learning based virtual sensing of head-mounted microphones. Hearing Research, 408, 108294. https:\/\/doi.org\/10.1016\/j.heares.2021.108294","journal-title":"Hearing Research"}],"container-title":["Wireless Personal Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-022-09549-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11277-022-09549-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-022-09549-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T13:38:10Z","timestamp":1656596290000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11277-022-09549-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,10]]},"references-count":62,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["9549"],"URL":"https:\/\/doi.org\/10.1007\/s11277-022-09549-6","relation":{},"ISSN":["0929-6212","1572-834X"],"issn-type":[{"type":"print","value":"0929-6212"},{"type":"electronic","value":"1572-834X"}],"subject":[],"published":{"date-parts":[[2022,2,10]]},"assertion":[{"value":"7 January 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 February 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":"There is no Conflicts of interest\/Competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}