{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:48:46Z","timestamp":1740098926325,"version":"3.37.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319664286"},{"type":"electronic","value":"9783319664293"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-66429-3_1","type":"book-chapter","created":{"date-parts":[[2017,8,12]],"date-time":"2017-08-12T02:02:55Z","timestamp":1502503375000},"page":"3-19","source":"Crossref","is-referenced-by-count":5,"title":["Low-Resource Speech Recognition and Keyword-Spotting"],"prefix":"10.1007","author":[{"given":"Mark J. F.","family":"Gales","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kate M.","family":"Knill","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anton","family":"Ragni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,8,13]]},"reference":[{"key":"1_CR1","unstructured":"The unicode consortium. http:\/\/www.unicode.org . Accessed 30 Sep 2014"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Beyerlein, P.: Discriminative model combination. In: Proceedings of ASRU (1997)","DOI":"10.1109\/ASRU.1997.659011"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., Ragni, A., Liu, X., Vasilakes, J., Knill, K.M., Gales, M.J.: Recurrent neural network language models for keyword search. In: ICASSP (2017)","DOI":"10.1109\/ICASSP.2017.7953263"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Cui, J., Kingsbury, B., Ramabhadran, B., Sethy, A., Audhkhasi, K., Cui, X., Kislal, E., Mangu, L., Nussbaum-Thom, M., Picheny, M., et al.: Multilingual representations for low resource speech recognition and keyword search. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 259\u2013266. IEEE (2015)","DOI":"10.1109\/ASRU.2015.7404803"},{"issue":"9","key":"1_CR5","doi-asserted-by":"crossref","first-page":"1469","DOI":"10.1109\/TASLP.2015.2438544","volume":"23","author":"X Cui","year":"2015","unstructured":"Cui, X., Goel, V., Kingsbury, B.: Data augmentation for deep neural network acoustic modeling. IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP) 23(9), 1469\u20131477 (2015)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP)"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Evermann, G., Woodland, P.C.: Large vocabulary decoding and confidence estimation using word posterior probabilities. In: Proceedings of ICASSP (2000)","DOI":"10.1109\/ICASSP.2000.862067"},{"key":"1_CR7","unstructured":"Evermann, G., Woodland, P.: Posterior probability decoding, confidence estimation and system combination. In: Proceedings of Speech Transcription Workshop, vol. 27, p. 78, Baltimore (2000)"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Fiscus, J.G.: A post-processing system to yield reduced word error rates: recogniser output voting error reduction (ROVER). In: Proceedings of ASRU (1997)","DOI":"10.1109\/ASRU.1997.659110"},{"key":"1_CR9","unstructured":"Fiscus, J.G., et al.: Results of the 2006 spoken term detection evaluation. In: Proceedings of ACM SIGIR Workshop on Searching Spontaneous Conversational Speech (2007)"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Gales, M.J., Knill, K.M., Ragni, A.: Unicode-based graphemic systems for limited resource languages. In: ICASSP, pp. 5186\u20135190. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178960"},{"key":"1_CR11","unstructured":"Gales, M.J., Knill, K.M., Ragni, A., Rath, S.P.: Speech recognition and keyword spotting for low-resource languages: Babel project research at cued. In: SLTU. pp. 16\u201323 (2014)"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Grezl, F., Karafiat, M., Janda, M.: Study of probabilistic and bottle-neck features in multilingual environment. In: Proceedings of ASRU (2011)","DOI":"10.1109\/ASRU.2011.6163958"},{"key":"1_CR13","unstructured":"Harper, M.: IARPA Babel Program. http:\/\/www.iarpa.gov\/Programs\/ia\/Babel\/babel.html"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Hartmann, W., Ng, T., Hsiao, R., Tsakalidis, S., Schwartz, R.: Two-stage data augmentation for low-resourced speech recognition. In: Interspeech 2016, pp. 2378\u20132382 (2016)","DOI":"10.21437\/Interspeech.2016-1386"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Hermansky, H., Ellis, D., Sharma, S.: Tandem connectionist feature extraction for conventional HMM systems. In: Proceedings of ICASSP (2000)","DOI":"10.1109\/ICASSP.2000.862024"},{"issue":"6","key":"1_CR16","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., Deng, L., et al.: Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Process. Mag. 29(6), 82\u201397 (2012)","journal-title":"IEEE Signal Process. Mag."},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Kanthak, S., Ney, H.: Context-dependent acoustic modelling using graphemes for large-vocabulary speech recognition. In: Proceedings of ICASSP (2002)","DOI":"10.1109\/ICASSP.2002.5743871"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Killer, M., St\u00fcker, S., Schultz, T.: Grapheme based speech recognition. In: Proceedings of EUROSPEECH (2003)","DOI":"10.21437\/Eurospeech.2003-785"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Mamou, J., Cui, J., Cui, X., Gales, M.J., Kingsbury, B., Knill, K., Mangu, L., Nolden, D., Picheny, M., Ramabhadran, B., et al.: System combination and score normalization for spoken term detection. In: ICASSP, pp. 8272\u20138276. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639278"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Mendels, G., Cooper, E., Soto, V., Hirschberg, J., Gales, M.J., Knill, K.M., Ragni, A., Wang, H.: Improving speech recognition and keyword search for low resource languages using web data. In: INTERSPEECH, pp. 829\u2013833 (2015)","DOI":"10.21437\/Interspeech.2015-260"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Karafi\u00e1t, M., Burget, L., Cernock\u1ef3, J., Khudanpur, S.: Recurrent neural network based language model. In: Interspeech, vol. 2, p. 3 (2010)","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Miller, D.R.H., Kleber, M., et al.: Rapid and accurate spoken term detection. In: Proceedings of Interspeech (2007)","DOI":"10.21437\/Interspeech.2007-174"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Ragni, A., Knill, K.M., Rath, S.P., Gales, M.J.F.: Data augmentation for low resource languages. In: Proceedings of InterSpeech (2014)","DOI":"10.21437\/Interspeech.2014-207"},{"key":"1_CR24","doi-asserted-by":"crossref","first-page":"3042","DOI":"10.21437\/Interspeech.2016-371","volume":"8","author":"A Ragni","year":"2016","unstructured":"Ragni, A., Dakin, E., Chen, X., Gales, M.J., Knill, K.M.: Multi-language neural network language models. Interspeech 8, 3042\u20133046 (2016)","journal-title":"Interspeech"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Ragni, A., Wu, C., Gales, M.J., Vasilakes, J., Knill, K.M.: Stimulated training for automatic speech recognition and keyword search in limited resource conditions. In: ICASSP (2017)","DOI":"10.1109\/ICASSP.2017.7953074"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Rath, S.P., Knill, K.M., Ragni, A., Gales, M.J.: Combining tandem and hybrid systems for improved speech recognition and keyword spotting on low resource languages. In: INTERSPEECH, pp. 835\u2013839 (2014)","DOI":"10.21437\/Interspeech.2014-212"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Swietojanski, P., Ghoshal, A., Renals, S.: Revisiting hybrid and gmm-hmm system combination techniques. In: ICASSP, pp. 6744\u20136748. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6638967"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Szoke, I., Burget, L., Cernocky, J., Fapso, M.: Sub-word modeling of out of vocabulary words in spoken term detection. In: Proceedings of SLT (2008)","DOI":"10.1109\/SLT.2008.4777893"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Tan, S., Sim, K.C., Gales, M.: Improving the interpretability of deep neural networks with stimulated learning. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 617\u2013623. IEEE (2015)","DOI":"10.1109\/ASRU.2015.7404853"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Vergyri, D., Shafran, I., et al.: The SRI\/OGI 2006 spoken term detection system. In: Proceedings of Interspeech (2007)","DOI":"10.21437\/Interspeech.2007-182"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Wang, H., Ragni, A., Gales, M.J., Knill, K.M., Woodland, P.C., Zhang, C.: Joint decoding of tandem and hybrid systems for improved keyword spotting on low resource languages. In: INTERSPEECH, pp. 3660\u20133664 (2015)","DOI":"10.21437\/Interspeech.2015-726"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Wu, C., Karanasou, P., Gales, M.J., Sim, K.C.: Stimulated deep neural network for speech recognition. In: Proceedings of Interspeech, pp. 400\u2013404 (2016)","DOI":"10.21437\/Interspeech.2016-580"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Yang, J., Zhang, C., Ragni, A., Gales, M.J., Woodland, P.C.: System combination with log-linear models. In: ICASSP, pp. 5675\u20135679. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472764"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, L., Karakos, D., Hartmann, W., Hsiao, R., Schwartz, R., Tsakalidis, S.: Enhancing low resource keyword spotting with automatically retrieved web documents. In: Interspeech (2015)","DOI":"10.21437\/Interspeech.2015-262"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-66429-3_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T00:49:29Z","timestamp":1692924569000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-66429-3_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319664286","9783319664293"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-66429-3_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}