{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T15:48:25Z","timestamp":1777650505185,"version":"3.51.4"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,6,5]],"date-time":"2019-06-05T00:00:00Z","timestamp":1559692800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,6,5]],"date-time":"2019-06-05T00:00:00Z","timestamp":1559692800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100012645","name":"University of Texas at Dallas","doi-asserted-by":"crossref","award":["Distinguished University Chair in Telecommunications Engineering"],"award-info":[{"award-number":["Distinguished University Chair in Telecommunications Engineering"]}],"id":[{"id":"10.13039\/501100012645","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1007\/s10772-019-09590-0","type":"journal-article","created":{"date-parts":[[2019,6,5]],"date-time":"2019-06-05T04:36:51Z","timestamp":1559709411000},"page":"697-709","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Speech and language processing for assessing child\u2013adult interaction based on diarization and location"],"prefix":"10.1007","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1382-9929","authenticated-orcid":false,"given":"John H. L.","family":"Hansen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maryam","family":"Najafian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rasa","family":"Lileikyte","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dwight","family":"Irvin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beth","family":"Rous","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,6,5]]},"reference":[{"issue":"2","key":"9590_CR1","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1109\/TASL.2011.2125954","volume":"20","author":"X Anguera","year":"2012","unstructured":"Anguera, X., Bozonnet, S., Evans, N., Fredouille, C., Friedland, G., & Vinyals, O. (2012). Speaker diarization: A review of recent research. IEEE Transactions on Audio, Speech, and Language Processing, 20(2), 356\u2013370.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9590_CR2","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.engappai.2014.05.003","volume":"34","author":"MH Bahari","year":"2014","unstructured":"Bahari, M. H., McLaren, M., van Leeuwen, D. A., et al. (2014). Speaker age estimation using i-vectors. Engineering Applications of Artificial Intelligence, 34, 99\u2013108.","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"5","key":"9590_CR3","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1109\/TASL.2006.878261","volume":"14","author":"C Barras","year":"2006","unstructured":"Barras, C., Zhu, X., Meignier, S., & Gauvain, J.-L. (2006). Multistage speaker diarization of broadcast news. IEEE Transactions on Audio, Speech, and Language Processing, 14(5), 1505\u20131512.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9590_CR4","unstructured":"Boersma, P. (1993). Accurate short-term analysis of the fundamental frequency and the harmonics-to-noise ratio of a sampled sound. In: Proceedings of the institute of phonetic sciences (Vol.\u00a017, pp. 97\u2013110). Amsterdam."},{"key":"9590_CR5","unstructured":"Bonastre, J.-F., Scheffer, N., Matrouf, D., Fredouille, C., Larcher, A., Preti, A., Pouchoulin, G., Evans, N.W., Fauve, B.G., & Mason, J.S. (2008). ALIZE\/spkdet: A state-of-the-art open source software for speaker recognition. In: Odyssey. p.\u00a020."},{"key":"9590_CR6","unstructured":"Connaghan, D., Hughes, S., May, G., Kelly, P., Conaire, C.\u00d3., O\u2019Connor, N.E., O\u2019Gorman, D., Smeaton, A.F., & Moyna, N. (2009). A sensing platform for physiological and contextual feedback to tennis athletes. In: Wearable and implantable body sensor networks, 2009 (pp. 224\u2013229). BSN 2009. IEEE."},{"issue":"3","key":"9590_CR7","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273\u2013297.","journal-title":"Machine Learning"},{"issue":"4","key":"9590_CR8","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","unstructured":"Dehak, N., Kenny, P. J., Dehak, R., Dumouchel, P., & Ouellet, P. (2011a). Front-end factor analysis for speaker verification. IEEE Transactions on Audio, Speech, and Language Processing, 19(4), 788\u2013798.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9590_CR9","doi-asserted-by":"crossref","unstructured":"Dehak, N., Torres-Carrasquillo, P.A., Reynolds, D., & Dehak, R. (2011b). Language recognition via i-vectors and dimensionality reduction. In Twelfth Annual Conference of the International Speech Communication Association, INTERSPEECH.","DOI":"10.21437\/Interspeech.2011-328"},{"issue":"1","key":"9590_CR10","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1177\/10983007060080010501","volume":"8","author":"M Delano","year":"2006","unstructured":"Delano, M., & Snell, M. E. (2006). The effects of social stories on the social engagement of children with autism. Journal of Positive Behavior Interventions, 8(1), 29\u201342.","journal-title":"Journal of Positive Behavior Interventions"},{"key":"9590_CR11","unstructured":"Gauvain, J.-L., & Lee, C.-H. (1991). Bayesian learning of Gaussian mixture densities for hidden Markov models. In Speech and natural language: Proceedings of a Workshop Held at Pacific Grove, California, 19-22 February, 1991."},{"key":"9590_CR12","doi-asserted-by":"crossref","unstructured":"Ghaemmaghami, H., Dean, D., & Sridharan, S. (2015). A cluster-voting approach for speaker diarization and linking of Australian broadcast news recordings. In ICASSP (pp. 4829\u20134833). IEEE.","DOI":"10.1109\/ICASSP.2015.7178888"},{"key":"9590_CR13","doi-asserted-by":"crossref","unstructured":"Ghaemmaghami, H., Dean, D., Vogt, R. & Sridharan, S. (2011). Extending the task of diarization to speaker attribution. In Interspeech 2011, 28\u201331 August 2011, Florence.","DOI":"10.21437\/Interspeech.2011-391"},{"key":"9590_CR14","doi-asserted-by":"crossref","unstructured":"Graciarena, M., Alwan, A., Ellis, D., Franco, H., Ferrer, L., Hansen, J.H., Janin, A., Lee, B.S., Lei, Y., & Mitra, V., et\u00a0al., (2013). All for one: feature combination for highly channel-degraded speech activity detection. In INTERSPEECH (pp. 709\u2013713).","DOI":"10.21437\/Interspeech.2013-199"},{"key":"9590_CR15","unstructured":"Gravier, G., Betser, M., & Ben, M. (2010). AudioSeg: Audio segmentation toolkit, release 1.2. IRISA, January."},{"key":"9590_CR16","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.csl.2015.09.003","volume":"37","author":"R Gupta","year":"2016","unstructured":"Gupta, R., Bone, D., Lee, S., & Narayanan, S. (2016). Analysis of engagement behavior in children during dyadic interactions using prosodic cues. Computer Speech & Language, 37, 47\u201366.","journal-title":"Computer Speech & Language"},{"key":"9590_CR17","volume-title":"Meaningful differences in the everyday experience of young American children","author":"B Hart","year":"1995","unstructured":"Hart, B., & Risley, T. R. (1995). Meaningful differences in the everyday experience of young American children. Baltimore, MD: Paul H Brookes Publishing."},{"key":"9590_CR18","unstructured":"Huijbregts, M. A.H. (2008). Segmentation, diarization and speech transcription: Surprise data unraveled. Ph.D. thesis, Centre for Telematics and Information Technology University of Twente."},{"issue":"9","key":"9590_CR19","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1007\/s10803-010-0955-5","volume":"40","author":"C Kasari","year":"2010","unstructured":"Kasari, C., Gulsrud, A. C., Wong, C., Kwon, S., & Locke, J. (2010). Randomized controlled caregiver mediated joint engagement intervention for toddlers with autism. Journal of Autism and Developmental Disorders, 40(9), 1045\u20131056.","journal-title":"Journal of Autism and Developmental Disorders"},{"key":"9590_CR20","unstructured":"Meignier, S., & Merlin, T. (2010). Lium spkdiarization: an open source toolkit for diarization. In CMU SPUD Workshop (Vol.\u00a02010). Le Mans: Universite du Maine."},{"issue":"2","key":"9590_CR21","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.csl.2005.08.002","volume":"20","author":"S Meignier","year":"2006","unstructured":"Meignier, S., Moraru, D., Fredouille, C., Bonastre, J.-F., & Besacier, L. (2006). Step-by-step and integrated approaches in broadcast news speaker diarization. Computer Speech & Language, 20(2), 303\u2013330.","journal-title":"Computer Speech & Language"},{"key":"9590_CR22","doi-asserted-by":"crossref","unstructured":"Najafian, M., Irvin, D., Luo, Y., Rous, B.S., & Hansen, J.H. (2016). Employing speech and location information for automatic assessment of child language environments. In Sensing, processing and learning for intelligent machines (SPLINE). IEEE, pp. 1\u20135.","DOI":"10.1109\/SPLIM.2016.7528412"},{"key":"9590_CR23","unstructured":"Phebey, T. (2010). The Ubisense assembly control solution for BMW solution for BMW. Proccedings of RFID Journal Europe Live. Retrieved 18 August, 2016."},{"key":"9590_CR24","doi-asserted-by":"crossref","unstructured":"Reynolds, D.A., Singer, E., Carlson, B.A., O\u2019Leary, G.C., McLaughlin, J.J., & Zissman, M.A. (1998). Blind clustering of speech utterances based on speaker and language characteristics. In Fifth International Conference on spoken language processing\u2014ICSP.","DOI":"10.21437\/ICSLP.1998-255"},{"key":"9590_CR25","doi-asserted-by":"crossref","unstructured":"Riehle, T.H., Lichter, P., Giudice, N.A. (2008). An indoor navigation system to support the visually impaired. In Engineering in Medicine and Biology Society, 2008. EMBS 2008. 30th Annual International Conference of the IEEE. IEEE, pp. 4435\u20134438.","DOI":"10.1109\/IEMBS.2008.4650195"},{"issue":"3","key":"9590_CR26","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1109\/LSP.2013.2237903","volume":"20","author":"SO Sadjadi","year":"2013","unstructured":"Sadjadi, S. O., & Hansen, J. H. (2013). Unsupervised speech activity detection using voicing measures and perceptual spectral flux. IEEE Signal Processing Letters, 20(3), 197\u2013200.","journal-title":"IEEE Signal Processing Letters"},{"key":"9590_CR27","doi-asserted-by":"crossref","unstructured":"Safavi, S., Russell, M., & Jan\u010dovi\u010d, P. (2014). Identification of age-group from children\u2019s speech by computers and humans. In Fifteenth Annual Conference of the International Speech Communication Association\u2014INTERSPEECH.","DOI":"10.21437\/Interspeech.2014-61"},{"key":"9590_CR28","doi-asserted-by":"crossref","unstructured":"Scheirer, E., & Slaney, M. (1997). Construction and evaluation of a robust multifeature speech\/music discriminator. In IEEE International Conference on acoustics, speech, and signal processing, 1997. IEEE. ICASSP-97 (Vol.\u00a02, pp. 1331\u20131334).","DOI":"10.1109\/ICASSP.1997.596192"},{"key":"9590_CR29","unstructured":"Siegler, M.A., Jain, U., Raj, B., & Stern, R.M., (1997). Automatic segmentation, classification and clustering of broadcast news audio. In Proceedings of DARPA speech recognition workshop. Vol.\u00a01997."},{"key":"9590_CR30","first-page":"2009","volume":"1","author":"C Swedberg","year":"2011","unstructured":"Swedberg, C. (2011). Bmw finds the right tool. RFID Journal, 1, 2009.","journal-title":"RFID Journal"},{"issue":"5","key":"9590_CR31","doi-asserted-by":"publisher","first-page":"1557","DOI":"10.1109\/TASL.2006.878256","volume":"14","author":"SE Tranter","year":"2006","unstructured":"Tranter, S. E., & Reynolds, D. A. (2006). An overview of automatic speaker diarization systems. IEEE Transactions on Audio, Speech, and Language Processing, 14(5), 1557\u20131565.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9590_CR32","doi-asserted-by":"crossref","unstructured":"Vijayasenan, D., & Valente, F. (2012). Diartk: An open source toolkit for research in multistream speaker diarization and its application to meetings recordings. In Thirteenth Annual Conference of the International Speech Communication Association\u2014INTERSPEECH. Portland.","DOI":"10.21437\/Interspeech.2012-579"},{"key":"9590_CR38","doi-asserted-by":"publisher","first-page":"606","DOI":"10.2307\/1131404","volume":"65","author":"D Walker","year":"1994","unstructured":"Walker, D., Greenwood, C., Hart, B., & Carta, J. (1994). Prediction of school outcomes based on early language production and socioeconomic factors. Child Development, 65, 606\u2013621.","journal-title":"Child Development"},{"issue":"1","key":"9590_CR33","doi-asserted-by":"crossref","first-page":"36","DOI":"10.2478\/rgg-2013-0011","volume":"95","author":"M Wo\u017aniak","year":"2013","unstructured":"Wo\u017aniak, M., Odziemczyk, W., & Nag\u00f3rski, K. (2013). Investigation of practical and theoretical accuracy of wireless indoor positioning system ubisense. Reports on Geodesy and Geoinformatics, 95(1), 36\u201348.","journal-title":"Reports on Geodesy and Geoinformatics"},{"key":"9590_CR34","unstructured":"Yella, S. H. (2015). Speaker diarization of spontaneous meeting room conversations. PhD thesis, EPFL, Lausanne."},{"issue":"5","key":"9590_CR35","first-page":"505","volume":"71","author":"Q Zhao","year":"1988","unstructured":"Zhao, Q., Kawamata, M., & Higuchi, T. (1988). Controllability, observability and model reduction of separable denominator MD systems. IEICE Transactions (1976\u20131990), 71(5), 505\u2013513.","journal-title":"IEICE Transactions (1976\u20131990)"},{"key":"9590_CR36","doi-asserted-by":"crossref","unstructured":"Ziaei, A., Kaushik, L., Sangwan, A., Hansen, J.H., & Oard, D.W. (2014). Speech activity detection for nasa apollo space missions: Challenges and solutions. In Fifteenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2014-369"},{"key":"9590_CR37","doi-asserted-by":"crossref","unstructured":"Ziaei, A., Sangwan, A., & Hansen, J.H. (2013). Prof-Life-Log: Personal interaction analysis for naturalistic audio streams. In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 7770\u20137774). IEEE.","DOI":"10.1109\/ICASSP.2013.6639176"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-019-09590-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-019-09590-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-019-09590-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T13:48:14Z","timestamp":1663595294000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-019-09590-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,5]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,9]]}},"alternative-id":["9590"],"URL":"https:\/\/doi.org\/10.1007\/s10772-019-09590-0","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6,5]]},"assertion":[{"value":"9 August 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 January 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 June 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}