{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:48:53Z","timestamp":1740098933907,"version":"3.37.3"},"publisher-location":"Cham","reference-count":17,"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_11","type":"book-chapter","created":{"date-parts":[[2017,8,11]],"date-time":"2017-08-11T22:02:55Z","timestamp":1502488975000},"page":"119-129","source":"Crossref","is-referenced-by-count":0,"title":["An Analysis of the RNN-Based Spoken\u00a0Term\u00a0Detection Training"],"prefix":"10.1007","author":[{"given":"Jan","family":"\u0160vec","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lubo\u0161","family":"\u0160m\u00eddl","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josef V.","family":"Psutka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,8,13]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Chen, G., Yilmaz, O., Trmal, J., Povey, D., Khudanpur, S.: Using proxies for OOV keywords in the keyword search task. In: IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013 - Proceedings, pp. 416\u2013421 (2013)","DOI":"10.1109\/ASRU.2013.6707766"},{"key":"11_CR2","first-page":"51","volume":"7","author":"JG Fiscus","year":"2007","unstructured":"Fiscus, J.G., Ajot, J., Garofolo, J.S., Doddington, G.: Results of the 2006 spoken term detection evaluation. Proc. ACM SIGIR Conf. 7, 51\u201357 (2007)","journal-title":"Proc. ACM SIGIR Conf."},{"key":"11_CR3","unstructured":"Goodfellow, I.J., Warde-farley, D., Mirza, M., Courville, A., Bengio, Y.: Maxout networks. In: Proceedings of International Conference on Machine Learning (2013)"},{"key":"11_CR4","unstructured":"He, W., Wang, W., Livescu, K.: Multi-view recurrent neural acoustic word embeddings. Appearing in ICLR 2017, pp. 1\u201312 (2017). http:\/\/arxiv.org\/abs\/1611.04496v2"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Kamper, H., Wang, W., Livescu, K.: Deep convolutional acoustic word embeddings using word-pair side information. In: IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 4950\u20134954, May 2016","DOI":"10.1109\/ICASSP.2016.7472619"},{"key":"11_CR6","unstructured":"Kingma, D.P.: ADAM: a method for stochastic optimization. In: Proceedings of 3rd International Conference for Learning Representations, pp. 1\u201315 (2015)"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Mamou, J., et al.: System combination and score normalization for spoken term detection. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 8272\u20138276 (2013)","DOI":"10.1109\/ICASSP.2013.6639278"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Mamou, J., Ramabhadran, B., Siohan, O.: Vocabulary independent spoken term detection. In: Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 615\u2013622 (2007)","DOI":"10.1145\/1277741.1277847"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Mangu, L., Soltau, H., Kuo, H.K., Kingsbury, B., Saon, G.: Exploiting diversity for spoken term detection. In: IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, ICASSP, (1), pp. 8282\u20138286 (2013)","DOI":"10.1109\/ICASSP.2013.6639280"},{"key":"11_CR10","unstructured":"Naaman, E., Adi, Y., Keshet, J.: Learning Similarity Function for Pronunciation Variations (2017). http:\/\/arxiv.org\/abs\/1703.09817"},{"key":"11_CR11","unstructured":"Povey, D., Ghoshal, A., Goel, N., Hannemann, M., Qian, Y., Schwarz, P., Stemmer, G.: The Kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding. IEEE, Big Island, Hawaii (2011)"},{"key":"11_CR12","unstructured":"Psutka, J., Radov\u00e1, V., Ircing, P., Matou\u0161ek, J., M\u00fcller, L.: USC-SFI MALACH Interviews and Transcripts Czech LDC2014S04 (2014). https:\/\/catalog.ldc.upenn.edu\/LDC2014S04"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Psutka, J., \u0160vec, J., Psutka, J.V., Van\u011bk, J., Pra\u017e\u00e1k, A., \u0160m\u00eddl, L., Ircing, P.: System for fast lexical and phonetic spoken term detection in a Czech cultural heritage archive. EURASIP J. Audio Speech Music Process. (1), 10 (2011)","DOI":"10.1186\/1687-4722-2011-10"},{"key":"11_CR14","unstructured":"Ramabhadran, B., Gustman, S., Byrne, W., Haji\u010d, J., Oard, D., Olsson, J.S., Picheny, M., Psutka, J.: USC-SFI MALACH Interviews and Transcripts English LDC2012S05 (2012). https:\/\/catalog.ldc.upenn.edu\/LDC2012s05"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Settle, S., Livescu, K.: Discriminative acoustic word embeddings: recurrent neural network-based approaches. In: IEEE Workshop on Spoken Language Technology (SLT), pp. 503\u2013510 (2016)","DOI":"10.1109\/SLT.2016.7846310"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"\u0160vec, J., Psutka, J.V., \u0160m\u00eddl, L., Trmal, J.: A relevance score estimation for spoken term detection based on RNN-generated pronunciation embeddings. In: Proceedings of Interspeech (2017). (to appear)","DOI":"10.21437\/Interspeech.2017-1087"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Wegmann, S., Faria, A., Janin, A., Riedhammer, K., Morgan, N.: The TAO of ATWV: probing the mysteries of keyword search performance. In: IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 192\u2013197 (2013)","DOI":"10.1109\/ASRU.2013.6707728"}],"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_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,2]],"date-time":"2019-10-02T06:13:33Z","timestamp":1569996813000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-66429-3_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319664286","9783319664293"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-66429-3_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}