{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T03:13:22Z","timestamp":1761621202752},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2014,12,1]],"date-time":"2014-12-01T00:00:00Z","timestamp":1417392000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1186\/s13636-014-0043-4","type":"journal-article","created":{"date-parts":[[2014,12,18]],"date-time":"2014-12-18T20:27:16Z","timestamp":1418934436000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["The self-taught vocal interface"],"prefix":"10.1186","volume":"2014","author":[{"given":"Bart","family":"Ons","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jort F","family":"Gemmeke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hugo Van","family":"hamme","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,12,19]]},"reference":[{"key":"43_CR1","volume-title":"Using Voice to Control the Civil Flightdeck (Technical Report, NLR-TP-2006-720","author":"G Zon","year":"2007","unstructured":"G Zon, M Roerdink, Using Voice to Control the Civil Flightdeck (Technical Report, NLR-TP-2006-720, National Aerospace Laboratory Amsterdam, Nederland, 2007)."},{"issue":"6","key":"43_CR2","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1109\/89.876308","volume":"8","author":"R Kuhn","year":"2000","unstructured":"Kuhn R, Junqua J-C, Nguyen P, Niedzielski N: Rapid speaker adaptation in eigenvoice space. IEEE Trans. Speech Audio Process 2000, 8(6):695-707. 10.1109\/89.876308","journal-title":"IEEE Trans. Speech Audio Process"},{"key":"43_CR3","first-page":"177","volume-title":"AVSP 2001-International Conference on Auditory-Visual Speech Processing.","author":"G Potamianos","year":"2001","unstructured":"G Potamianos, C Neti, in AVSP 2001-International Conference on Auditory-Visual Speech Processing. Automatic speechreading of impaired speech (Volterra, Italy, 2001), pp. 177\u2013182."},{"key":"43_CR4","first-page":"11","volume-title":"Proc SLPAT.","author":"F Rudzicz","year":"2011","unstructured":"F Rudzicz, in Proc SLPAT. Acoustic transformations to improve the intelligibility of dysarthric speech (Association for Computational LinguisticsEdinburgh, Scotland, 2011), pp. 11\u201321."},{"key":"43_CR5","first-page":"1189","volume-title":"Proc Interspeech","author":"P Green","year":"2003","unstructured":"P Green, J Carmichael, A Hatzis, P Enderby, MS Hawley, M Parker, in Proc Interspeech. Automatic speech recognition with sparse training data for dysarthric speakers (Geneva, Switzerland, 2003), pp. 1189\u20131192."},{"issue":"2-3","key":"43_CR6","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1080\/02699200400026884","volume":"20","author":"M Parker","year":"2006","unstructured":"Parker M, Cunningham S, Enderby P, Hawley M, Green P: Automatic speech recognition and training for severely dysarthric users of assistive technology: the stardust project. Clin. Linguist. Phon 2006, 20(2-3):149-156. 10.1080\/02699200400026884","journal-title":"Clin. Linguist. Phon"},{"key":"43_CR7","volume-title":"Speech recognition in individuals with dysarthria.","author":"AM Acrey","year":"2012","unstructured":"AM Acrey, Speech recognition in individuals with dysarthria. PhD thesis, Texas Tech University (2012)."},{"key":"43_CR8","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/297860","volume-title":"Comput. Math. Methods Med. 2013","author":"S-O Caballero-Morales","year":"2013","unstructured":"S-O Caballero-Morales, Estimation of phoneme-specific HMM topologies for the automatic recognition of dysarthric speech. Comput. Math. Methods Med. 2013 (2013). doi:10.1155\/2013\/297860."},{"issue":"3","key":"43_CR9","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1016\/j.eswa.2013.08.014","volume":"41","author":"S-O Caballero-Morales","year":"2014","unstructured":"Caballero-Morales S-O, Trujillo-Romero F: Evolutionary approach for integration of multiple pronunciation patterns for enhancement of dysarthric speech recognition. Expert Syst. Appl 2014, 41(3):841-852. 10.1016\/j.eswa.2013.08.014","journal-title":"Expert Syst. Appl"},{"key":"43_CR10","first-page":"117","volume-title":"Computers Helping People with Special Needs. Lecture Notes in Computer Science, 7383","author":"Y Hwang","year":"2012","unstructured":"Y Hwang, D Shin, C-Y Yang, S-Y Lee, J Kim, B Kong, J Chung, S Kim, M Chung, in Computers Helping People with Special Needs. Lecture Notes in Computer Science, 7383, ed. by K Miesenberger, J Klaus, W Zagler, and A Karshmer. Developing a voice user interface with improved usability for people with dysarthria (Springer,Berlin Heidelberg, 2012), pp. 117\u2013124."},{"issue":"4","key":"43_CR11","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1080\/aac.17.4.265.275","volume":"17","author":"P Raghavendra","year":"2001","unstructured":"Raghavendra P, Rosengren E, Hunnicutt S: An investigation of different degrees of dysarthric speech as input to speaker-adaptive and speaker-dependent recognition systems. Augment. Altern. Commun 2001, 17(4):265-275. 10.1080\/aac.17.4.265.275","journal-title":"Augment. Altern. Commun"},{"key":"43_CR12","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1145\/1296843.1296899","volume-title":"Proceedings of the 9th International ACM SIGACCESS Conference on Computers and Accessibility. Assets \u201907.","author":"F Rudzicz","year":"2007","unstructured":"F Rudzicz, in Proceedings of the 9th International ACM SIGACCESS Conference on Computers and Accessibility. Assets \u201907. Comparing speaker-dependent and speaker-adaptive acoustic models for recognizing dysarthric speech (ACMNew York, NY, USA, 2007), pp. 255\u2013256. doi:10.1145\/1296843.1296899 . http:\/\/doi.acm.org\/10.1145\/1296843.1296899 ."},{"key":"43_CR13","first-page":"1613","volume-title":"Proc. Interspeech","author":"M Matassoni","year":"2014","unstructured":"M Matassoni, R Astudillo, A Natsamanis, M Ravanelli, in Proc. Interspeech. The dirha-grid corpus: baseline and tools for multi-room distant speech recognition using distributed microphones (Singapore, 2014), pp. 1613\u20131617."},{"key":"43_CR14","doi-asserted-by":"crossref","first-page":"2273","DOI":"10.21437\/Interspeech.2011-604","volume-title":"roc Interspeech.","author":"B Lecouteux","year":"2011","unstructured":"B Lecouteux, M Cacher, F Portet, in Proc Interspeech. Distant speech recognition in a smart home: comparison of several multisource ASRs in realistic conditions (Florence, Italy, 2011), pp. 2273\u20132276."},{"key":"43_CR15","first-page":"29","volume-title":"Proc SLPAT.","author":"H Christensen","year":"2013","unstructured":"H Christensen, I Casanuevo, S Cunningham, P Green, T Hain, in Proc SLPAT. homeService: voice-enabled assistive technology in the home using cloud-based automatic speech recognition (Grenoble, France, 2013), pp. 29\u201334."},{"key":"43_CR16","first-page":"2038","volume-title":"Self-taught assistive vocal interfaces: an overview of the ALADIN project","author":"J Gemmeke","year":"2013","unstructured":"J Gemmeke, B Ons, M Tessema, J van de Loo, G De Pauw, W Daelemans, J Huyghe, J Derboven, L Vuegen, B Van Den Broeck, H Van hamme, in Proc Interspeech. Self-taught assistive vocal interfaces: an overview of the ALADIN project (Lyon, France, 2013), pp. 2038\u20132043."},{"key":"43_CR17","volume-title":"Discovering words in speech using matrix factorization","author":"J Driesen","year":"2012","unstructured":"J Driesen, Discovering words in speech using matrix factorization. PhD thesis, K.U.Leuven, ESAT, July 2012."},{"key":"43_CR18","first-page":"1","volume-title":"Proc SLPAT.","author":"B Ons","year":"2013","unstructured":"B Ons, N Tessema, J van de Loo, JF Gemmeke, in Proc SLPAT. A self learning vocal interface for speech-impaired users (Grenoble, France, 2013), pp. 1\u20139."},{"issue":"3-4","key":"43_CR19","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1016\/j.specom.2005.07.001","volume":"48","author":"Y Wang","year":"2006","unstructured":"Wang Y, Acero A: Rapid development of spoken language understanding grammars. Speech Commun 2006, 48(3-4):390-416. 10.1016\/j.specom.2005.07.001","journal-title":"Speech Commun"},{"issue":"4","key":"43_CR20","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"SB Davis","year":"1980","unstructured":"Davis SB, Mermelstein P: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoustics Speech Signal Process 1980, 28(4):357-366. 10.1109\/TASSP.1980.1163420","journal-title":"IEEE Trans. Acoustics Speech Signal Process"},{"issue":"4","key":"43_CR21","doi-asserted-by":"publisher","first-page":"997","DOI":"10.1016\/j.csl.2014.03.004","volume":"28","author":"B Ons","year":"2014","unstructured":"Ons B, Gemmeke JF, Van hamme H: Fast vocabulary acquisition in an NMF-based self-learning vocal user interface. Comput. Speech Lang 2014, 28(4):997-1017. 10.1016\/j.csl.2014.03.004","journal-title":"Comput. Speech Lang"},{"key":"43_CR22","first-page":"255","volume-title":"Proc. Interspeech.","author":"H Van hamme","year":"2008","unstructured":"H Van hamme, in Proc. Interspeech. HAC-models: a novel approach to continuous speech recognition (Brisbane, Australia, 2008), pp. 255\u2013258."},{"key":"43_CR23","doi-asserted-by":"publisher","first-page":"1124","DOI":"10.1016\/j.specom.2009.05.003","volume":"51","author":"M Van Segbroeck","year":"2009","unstructured":"Van Segbroeck M, Van hamme H: Unsupervised learning of time-frequency patches as a noise-robust representation of speech. Speech Commun 2009, 51: 1124-1138. 10.1016\/j.specom.2009.05.003","journal-title":"Speech Commun"},{"key":"43_CR24","doi-asserted-by":"publisher","DOI":"10.1002\/9780470747278","volume-title":"Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-way Data Analysis and Blind Source Separation (John Wiley & Sons","author":"A Cichocki","year":"2009","unstructured":"A Cichocki, R Zdunek, A-H Phan, S Amari, Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-way Data Analysis and Blind Source Separation (John Wiley & Sons, Ltd chichester, United Kingdom, 2009)."},{"key":"43_CR25","volume-title":"16th Computer Vision Winter Workshop.","author":"Z Akata","year":"2011","unstructured":"Z Akata, C Thurau, C Bauckhage, in 16th Computer Vision Winter Workshop. Non-negative matrix factorization in multimodality data for segmentation and label prediction (Mitterberg, Austria, February 2\u20134 2011)."},{"issue":"1","key":"43_CR26","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/LSP.2009.2027163","volume":"17","author":"H Lee","year":"2010","unstructured":"Lee H, Yoo J, Choi S: Semi-supervised nonnegative matrix factorization. Signal Process. Lett. IEEE 2010, 17(1):4-7. 10.1109\/LSP.2009.2027163","journal-title":"Signal Process. Lett. IEEE"},{"key":"43_CR27","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1038\/44565","volume":"401","author":"DD Lee","year":"1999","unstructured":"Lee DD, Seung HS: Learning the parts of objects by nonnegative matrix factorization. Nature 1999, 401: 788-791. 10.1038\/44565","journal-title":"Nature"},{"key":"43_CR28","first-page":"21","volume-title":"Proc SLPAT.","author":"B Lize","year":"2013","unstructured":"B Lize, D Katrien, FG Jort, H Van hamme, in Proc SLPAT. Comparing and combining classifiers for self-taught vocal interfaces (Grenoble, France, 2013), pp. 21\u201328."},{"key":"43_CR29","volume-title":"Automatic analysis of pathological speech","author":"C Middag","year":"2012","unstructured":"C Middag, Automatic analysis of pathological speech. PhD thesis. Ghent University, Belgium, 2012."},{"issue":"368","key":"43_CR30","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1080\/01621459.1979.10481038","volume":"74","author":"WS Cleveland","year":"1979","unstructured":"Cleveland WS: Robust locally weighted regression and smoothing scatterplots. J. Am. Stat. Assoc 1979, 74(368):829-836. 10.1080\/01621459.1979.10481038","journal-title":"J. Am. Stat. Assoc"},{"issue":"403","key":"43_CR31","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1080\/01621459.1988.10478639","volume":"83","author":"WS Cleveland","year":"1988","unstructured":"Cleveland WS, Devlin SJ: Locally weighted regression: an approach to regression analysis by local fitting. J. Am. Stat. Assoc 1988, 83(403):596-610. 10.1080\/01621459.1988.10478639","journal-title":"J. Am. Stat. Assoc"},{"key":"43_CR32","first-page":"17","volume-title":"Proc at 15th International Conference on Digital Audio Effects DAFx-12.","author":"R Jaiswal","year":"2012","unstructured":"R Jaiswal, D Fitzgerald, E Coyle, S Rickard, in Proc at 15th International Conference on Digital Audio Effects DAFx-12. Shifted NMF with group sparsity for clustering NMF basis functions (York, UK, 2012), pp. 17\u201321."}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13636-014-0043-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-014-0043-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-014-0043-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-014-0043-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,24]],"date-time":"2022-04-24T15:31:21Z","timestamp":1650814281000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13636-014-0043-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,12]]}},"alternative-id":["43"],"URL":"https:\/\/doi.org\/10.1186\/s13636-014-0043-4","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,12]]},"assertion":[{"value":"31 January 2014","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 November 2014","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 December 2014","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"43"}}