{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T16:30:31Z","timestamp":1771000231513,"version":"3.50.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2020,10,27]],"date-time":"2020-10-27T00:00:00Z","timestamp":1603756800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,10,27]],"date-time":"2020-10-27T00:00:00Z","timestamp":1603756800000},"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":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1007\/s00034-020-01565-w","type":"journal-article","created":{"date-parts":[[2020,10,27]],"date-time":"2020-10-27T19:02:56Z","timestamp":1603825376000},"page":"1892-1904","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["A Pitch and Noise Robust Keyword Spotting System Using SMAC Features with Prosody Modification"],"prefix":"10.1007","volume":"40","author":[{"given":"Karabi","family":"Maity","sequence":"first","affiliation":[]},{"given":"Gayadhar","family":"Pradhan","sequence":"additional","affiliation":[]},{"given":"Jyoti Prakash","family":"Singh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,10,27]]},"reference":[{"key":"1565_CR1","doi-asserted-by":"crossref","unstructured":"A. Batliner, M. Blomberg, S. D\u2019Arcy, D. Elenius, D. Giuliani, M. Gerosa, C. Hacker, M. Russell, S. Steidl, M. Wong, The PF_STAR children\u2019s speech corpus, in INTERSPEECH, pp. 2761\u20132764 (2005)","DOI":"10.21437\/Interspeech.2005-705"},{"issue":"12","key":"1565_CR2","doi-asserted-by":"publisher","first-page":"15875","DOI":"10.1007\/s11042-017-5160-5","volume":"77","author":"A Becerra","year":"2018","unstructured":"A. Becerra, J.I. de la Rosa, E. Gonz\u00e1lez, Speech recognition in a dialog system: from conventional to deep processing. Multimed. Tools Appl. 77(12), 15875\u201315911 (2018)","journal-title":"Multimed. Tools Appl."},{"key":"1565_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.specom.2018.02.003","volume":"99","author":"H Benisty","year":"2018","unstructured":"H. Benisty, I. Katz, K. Crammer, D. Malah, Discriminative keyword spotting for limited-data applications. Speech Commun. 99, 1\u201311 (2018)","journal-title":"Speech Commun."},{"issue":"8","key":"1565_CR4","doi-asserted-by":"publisher","first-page":"2338","DOI":"10.1109\/TASL.2011.2134087","volume":"19","author":"D Can","year":"2011","unstructured":"D. Can, M. Saraclar, Lattice indexing for spoken term detection. IEEE Trans. Audio Speech Lang. Process. 19(8), 2338\u20132347 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"1565_CR5","doi-asserted-by":"crossref","unstructured":"G. Chen, C. Parada, G. Heigold, Small-footprint keyword spotting using deep neural networks, in Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4087\u20134091 (2014)","DOI":"10.1109\/ICASSP.2014.6854370"},{"issue":"2","key":"1565_CR6","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/s11265-015-0998-0","volume":"82","author":"IF Chen","year":"2016","unstructured":"I.F. Chen, C. Ni, B.P. Lim, N.F. Chen, C.H. Lee, A keyword-aware language modelling approach to spoken keyword search. J. Signal Process. Syst. 82(2), 197\u2013206 (2016)","journal-title":"J. Signal Process. Syst."},{"key":"1565_CR7","unstructured":"W.M. Fisher, Ther DARPA speech recognition research database: specifications and status, in Proceedings DARPA Workshop on Speech Recognition, Feb. 1986, pp. 93\u201399 (1986)"},{"key":"1565_CR8","doi-asserted-by":"crossref","unstructured":"M. Gerosa, D. Giuliani, S. Narayanan, A. Potamianos, A review of ASR technologies for children\u2019s speech, in Proceedings of the 2nd Workshop on Child, Computer and Interaction, pp. 7:1\u20137:8 (2009)","DOI":"10.1145\/1640377.1640384"},{"key":"1565_CR9","doi-asserted-by":"crossref","unstructured":"D.R.H. Miller, M. Kleber, C.L. Kao, O. Kimball, T. Colthurst, S.A. Lowe, R.M. Schwartz, H. Gish, Rapid and accurate spoken term detection, in Proceedings INTERSPEECH (2007)","DOI":"10.21437\/Interspeech.2007-174"},{"key":"1565_CR10","doi-asserted-by":"publisher","first-page":"1602","DOI":"10.1109\/TASL.2008.2004526","volume":"16","author":"KSR Murthy","year":"2008","unstructured":"K.S.R. Murthy, B. Yegnanarayana, Epoch extraction from speech signals. IEEE Trans. Audio Speech Lang. Process. 16, 1602\u20131613 (2008)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"5","key":"1565_CR11","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1049\/iet-spr.2019.0027","volume":"13","author":"B Pattanayak","year":"2019","unstructured":"B. Pattanayak, J.K. Rout, G. Pradhan, Adaptive spectral smoothening for development of robust keyword spotting system. IET Signal Proc. 13(5), 544\u2013550 (2019)","journal-title":"IET Signal Proc."},{"key":"1565_CR12","unstructured":"D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel, M. Hannemann, P. Motlicek, Y. Qian, P. Schwarz et\u00a0al., The Kaldi speech recognition toolkit, in Proceedings Automatic Speech Recognition and Understanding (2011)"},{"issue":"3","key":"1565_CR13","doi-asserted-by":"publisher","first-page":"972","DOI":"10.1109\/TSA.2005.858051","volume":"14","author":"KS Rao","year":"2006","unstructured":"K.S. Rao, B. Yegnanarayana, Prosody modification using instants of significant excitation. IEEE Trans. Audio Speech Lang. Process. 14(3), 972\u2013980 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"1565_CR14","doi-asserted-by":"crossref","unstructured":"S.P. Rath, D. Povey, K. Vesel\u1ef3, J. Cernock\u1ef3, Improved feature processing for deep neural networks, in Proceedings INTERSPEECH, pp. 109\u2013113 (2013)","DOI":"10.21437\/Interspeech.2013-48"},{"key":"1565_CR15","doi-asserted-by":"crossref","unstructured":"T. Robinson, J. Fransen, D. Pye, J. Foote, S. Renals, WSJCAMO: a British English speech corpus for large vocabulary continuous speech recognition, in 1995 International Conference on Acoustics, Speech, and Signal Processing. vol.\u00a01, pp. 81\u201384. IEEE (1995)","DOI":"10.1109\/ICASSP.1995.479278"},{"key":"1565_CR16","doi-asserted-by":"crossref","unstructured":"M. Russell, S. D\u2019Arcy, Challenges for computer recognition of children\u2019s speech, in Speech and Language Technology in Education (SLaTE2007), pp. 108\u2013111 (2007)","DOI":"10.21437\/SLaTE.2007-26"},{"issue":"5","key":"1565_CR17","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1007\/s11265-016-1202-x","volume":"90","author":"M Shah","year":"2018","unstructured":"M. Shah, S. Arunachalam, J. Wang, D. Blaauw, D. Sylvester, H.S. Kim, J.S. Seo, C. Chakrabarti, A fixed-point neural network architecture for speech applications on resource-constrained hardware. J. Signal Process. Syst. 90(5), 727\u2013741 (2018)","journal-title":"J. Signal Process. Syst."},{"key":"1565_CR18","doi-asserted-by":"crossref","unstructured":"S. Shahnawazuddin, A. Dey, R. Sinha, Pitch-adaptive front-end features for robust children\u2019s ASR, in Proceedings INTERSPEECH, pp. 3459\u20133463 (2016)","DOI":"10.21437\/Interspeech.2016-1020"},{"issue":"11","key":"1565_CR19","doi-asserted-by":"publisher","first-page":"1749","DOI":"10.1109\/LSP.2017.2756347","volume":"24","author":"S Shahnawazuddin","year":"2017","unstructured":"S. Shahnawazuddin, N. Adiga, H.K. Kathania, Effect of prosody modification on children\u2019s ASR. IEEE Signal Process. Lett. 24(11), 1749\u20131753 (2017)","journal-title":"IEEE Signal Process. Lett."},{"issue":"8","key":"1565_CR20","doi-asserted-by":"publisher","first-page":"1128","DOI":"10.1109\/LSP.2017.2705085","volume":"24","author":"S Shahnawazuddin","year":"2017","unstructured":"S. Shahnawazuddin, R. Sinha, G. Pradhan, Pitch-normalized acoustic features for robust children\u2019s speech recognition. IEEE Signal Process. Lett. 24(8), 1128\u20131132 (2017)","journal-title":"IEEE Signal Process. Lett."},{"key":"1565_CR21","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.dsp.2018.12.011","volume":"86","author":"S Shahnawazuddin","year":"2019","unstructured":"S. Shahnawazuddin, K. Maity, G. Pradhan, Improving the performance of keyword spotting system for children\u2019s speech through prosody modification. Digit. Signal Proc. 86, 11\u201318 (2019)","journal-title":"Digit. Signal Proc."},{"key":"1565_CR22","doi-asserted-by":"crossref","unstructured":"H. Sundar, J.F. Lehman, R. Singh, Keyword spotting in multi-player voice-driven games for children, in Proceedings Sixteenth Annual Conference of the International Speech Communication Association, pp. 1660\u20131664 (2015)","DOI":"10.21437\/Interspeech.2015-383"},{"issue":"6","key":"1565_CR23","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1109\/LSP.2010.2046349","volume":"17","author":"P Tsiakoulis","year":"2010","unstructured":"P. Tsiakoulis, A. Potamianos, D. Dimitriadis, Spectral moment features augmented by low order cepstral coefficients for robust ASR. IEEE Signal Process. Lett. 17(6), 551\u2013554 (2010)","journal-title":"IEEE Signal Process. Lett."},{"issue":"3","key":"1565_CR24","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"A Varga","year":"1993","unstructured":"A. Varga, H.J. Steeneken, Assessment for automatic speech recognition: II. Noisex-92: a database and an experiment to study the effect of additive noise on speech recognition systems. Speech Commun. 12(3), 247\u2013251 (1993)","journal-title":"Speech Commun."},{"key":"1565_CR25","doi-asserted-by":"crossref","unstructured":"S. Wegmann, A. Faria, A. Janin, K. Riedhammer, N. Morgan, The TAO of ATWV: probing the mysteries of keyword search performance, in 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 192\u2013197. IEEE (2013)","DOI":"10.1109\/ASRU.2013.6707728"},{"issue":"4","key":"1565_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1998384.1998386","volume":"7","author":"M W\u00f6llmer","year":"2011","unstructured":"M. W\u00f6llmer, B. Schuller, A. Batliner, S. Steidl, D. Seppi, Tandem decoding of children\u2019s speech for keyword detection in a child-robot interaction scenario. ACM Trans. Speech Lang. Process. (TSLP) 7(4), 1\u201322 (2011)","journal-title":"ACM Trans. Speech Lang. Process. (TSLP)"},{"key":"1565_CR27","unstructured":"Y.D. Wu, B.L. Liu, Keyword spotting method based on speech feature space trace matching, in Proceedings of the 2003 International Conference on Machine Learning and Cybernetics. vol.\u00a05, pp. 3188\u20133192. IEEE (2003)"},{"key":"1565_CR28","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.dsp.2018.12.013","volume":"86","author":"IC Yadav","year":"2019","unstructured":"I.C. Yadav, S. Shahnawazuddin, G. Pradhan, Addressing noise and pitch sensitivity of speech recognition system through variational mode decomposition based spectral smoothing. Digit. Signal Proc. 86, 55\u201364 (2019)","journal-title":"Digit. Signal Proc."},{"key":"1565_CR29","doi-asserted-by":"crossref","unstructured":"N. Zhao, H. Yang, Realizing speech to gesture conversion by keyword spotting. In: Proceedings Chinese Spoken Language Processing (ISCSLP), pp. 1\u20135 (2016)","DOI":"10.1109\/ISCSLP.2016.7918458"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-020-01565-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-020-01565-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-020-01565-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T14:10:21Z","timestamp":1723817421000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-020-01565-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,27]]},"references-count":29,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,4]]}},"alternative-id":["1565"],"URL":"https:\/\/doi.org\/10.1007\/s00034-020-01565-w","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,27]]},"assertion":[{"value":"21 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 October 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 October 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}