{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T13:09:09Z","timestamp":1748005749395,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031476648"},{"type":"electronic","value":"9783031476655"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-47665-5_28","type":"book-chapter","created":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T20:01:39Z","timestamp":1699128099000},"page":"346-357","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Transformer-Based Encoder-Encoder Architecture for\u00a0Spoken Term Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8362-5927","authenticated-orcid":false,"given":"Jan","family":"\u0160vec","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8169-2410","authenticated-orcid":false,"given":"Lubo\u0161","family":"\u0160m\u00eddl","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3889-8069","authenticated-orcid":false,"given":"Jan","family":"Lehe\u010dka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,5]]},"reference":[{"key":"28_CR1","unstructured":"Baevski, A., Zhou, H., Mohamed, A., Auli, M.: Wav2Vec 2.0: a framework for self-supervised learning of speech representations. In: Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS 2020. Curran Associates Inc., Red Hook, NY, USA (2020)"},{"key":"28_CR2","doi-asserted-by":"publisher","unstructured":"Berg, A., O\u2019Connor, M., Cruz, M.T.: Keyword transformer: a self-attention model for keyword spotting. In: Proceedings of Interspeech 2021, pp. 4249\u20134253 (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-1286","DOI":"10.21437\/Interspeech.2021-1286"},{"key":"28_CR3","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"28_CR4","doi-asserted-by":"publisher","unstructured":"Ding, K., Zong, M., Li, J., Li, B.: LETR: a lightweight and efficient transformer for keyword spotting. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7987\u20137991 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9747295","DOI":"10.1109\/ICASSP43922.2022.9747295"},{"key":"28_CR5","doi-asserted-by":"publisher","unstructured":"Gillioz, A., Casas, J., Mugellini, E., Khaled, O.A.: Overview of the transformer-based models for NLP tasks. In: 2020 15th Conference on Computer Science and Information Systems (FedCSIS), pp. 179\u2013183 (2020). https:\/\/doi.org\/10.15439\/2020F20","DOI":"10.15439\/2020F20"},{"key":"28_CR6","unstructured":"Google Research: TensorFlow code and pre-trained models for BERT, March 2020. https:\/\/github.com\/google-research\/bert"},{"key":"28_CR7","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian Error Linear Units (GELUs). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"28_CR8","doi-asserted-by":"publisher","unstructured":"Karita, S., et al.: A comparative study on transformer vs RNN in speech applications. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 449\u2013456 (2019). https:\/\/doi.org\/10.1109\/ASRU46091.2019.9003750","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"28_CR9","doi-asserted-by":"publisher","unstructured":"Lehe\u010dka, J., \u0160vec, J., Prazak, A., Psutka, J.: Exploring capabilities of monolingual audio transformers using large datasets in automatic speech recognition of Czech. In: Proceedings of Interspeech 2022, pp. 1831\u20131835 (2022). https:\/\/doi.org\/10.21437\/Interspeech.2022-10439","DOI":"10.21437\/Interspeech.2022-10439"},{"key":"28_CR10","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv (1), July 2019. http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"28_CR11","doi-asserted-by":"publisher","unstructured":"Luo, Z., et al.: DecBERT: enhancing the language understanding of BERT with causal attention masks. In: Findings of the Association for Computational Linguistics: NAACL 2022, pp. 1185\u20131197. Association for Computational Linguistics, Seattle, United States, July 2022. https:\/\/doi.org\/10.18653\/v1\/2022.findings-naacl.89, https:\/\/aclanthology.org\/2022.findings-naacl.89","DOI":"10.18653\/v1\/2022.findings-naacl.89"},{"key":"28_CR12","unstructured":"Meta Research: Wav2Vec 2.0, April 2022. https:\/\/github.com\/facebookresearch\/fairseq\/blob\/main\/examples\/wav2vec\/README.md"},{"key":"28_CR13","doi-asserted-by":"publisher","unstructured":"Ott, M., et al.: fairseq: a fast, extensible toolkit for sequence modeling. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations), pp. 48\u201353. Association for Computational Linguistics, Minneapolis, Minnesota, June 2019. https:\/\/doi.org\/10.18653\/v1\/N19-4009, https:\/\/aclanthology.org\/N19-4009","DOI":"10.18653\/v1\/N19-4009"},{"key":"28_CR14","unstructured":"Psutka, J., Radov\u00e1, V., Ircing, P., Matou\u0161ek, J., M\u00fcller, L.: USC-SFI MALACH Interviews and Transcripts Czech LDC2014S04. Linguistic Data Consortium, Philadelphia (2014). https:\/\/catalog.ldc.upenn.edu\/LDC2014S04"},{"key":"28_CR15","unstructured":"Ramabhadran, B., et al.: USC-SFI MALACH Interviews and Transcripts English LDC2012S05. Linguistic Data Consortium, Philadelphia (2012). https:\/\/catalog.ldc.upenn.edu\/LDC2012s05 (2012)"},{"key":"28_CR16","doi-asserted-by":"publisher","unstructured":"Settle, S., Livescu, K.: Discriminative acoustic word embeddings: recurrent neural network-based approaches. In: 2016 IEEE Spoken Language Technology Workshop (SLT), pp. 503\u2013510 (2016). https:\/\/doi.org\/10.1109\/SLT.2016.7846310","DOI":"10.1109\/SLT.2016.7846310"},{"key":"28_CR17","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5999\u20136009 (2017)"},{"key":"28_CR18","doi-asserted-by":"publisher","unstructured":"Wang, Y., Lv, H., Povey, D., Xie, L., Khudanpur, S.: Wake word detection with streaming transformers. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5864\u20135868 (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414777","DOI":"10.1109\/ICASSP39728.2021.9414777"},{"key":"28_CR19","doi-asserted-by":"publisher","unstructured":"Wegmann, S., Faria, A., Janin, A., Riedhammer, K., Morgan, N.: The TAO of ATWV: probing the mysteries of keyword search performance. In: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013 - Proceedings, pp. 192\u2013197 (2013). https:\/\/doi.org\/10.1109\/ASRU.2013.6707728","DOI":"10.1109\/ASRU.2013.6707728"},{"key":"28_CR20","doi-asserted-by":"publisher","unstructured":"Yang, D., et al.: CaTT-KWS: a multi-stage customized keyword spotting framework based on cascaded transducer-transformer. In: Proceedings of Interspeech 2022, pp. 1681\u20131685 (2022). https:\/\/doi.org\/10.21437\/Interspeech.2022-10258","DOI":"10.21437\/Interspeech.2022-10258"},{"key":"28_CR21","doi-asserted-by":"publisher","first-page":"1988","DOI":"10.1109\/TASLP.2020.2998277","volume":"28","author":"Y Yuan","year":"2020","unstructured":"Yuan, Y., Xie, L., Leung, C.C., Chen, H., Ma, B.: Fast query-by-example speech search using attention-based deep binary embeddings. IEEE\/ACM Trans. Audio Speech Lang. Process. 28, 1988\u20132000 (2020). https:\/\/doi.org\/10.1109\/TASLP.2020.2998277","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"28_CR22","doi-asserted-by":"publisher","unstructured":"\u0160vec, J., Lehe\u010dka, J., \u0160m\u00eddl, L.: Deep LSTM spoken term detection using Wav2Vec 2.0 recognizer. In: Proceedings of Interspeech 2022, pp. 1886\u20131890 (2022). https:\/\/doi.org\/10.21437\/Interspeech.2022-10409","DOI":"10.21437\/Interspeech.2022-10409"},{"key":"28_CR23","doi-asserted-by":"publisher","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, pp. 2934\u20132938 (2017). https:\/\/doi.org\/10.21437\/Interspeech.2017-1087","DOI":"10.21437\/Interspeech.2017-1087"},{"key":"28_CR24","doi-asserted-by":"publisher","unstructured":"\u0160vec, J., \u0160m\u00eddl, L., Psutka, J.V., Pra\u017e\u00e1k, A.: Spoken term detection and relevance score estimation using dot-product of pronunciation embeddings. In: Proceedings of Interspeech 2021, pp. 4398\u20134402 (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-1704","DOI":"10.21437\/Interspeech.2021-1704"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-47665-5_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T20:13:23Z","timestamp":1699128803000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-47665-5_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031476648","9783031476655"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-47665-5_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"5 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kitakyushu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ericlab.org\/acpr2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"164","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"93","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"57% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}