{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T00:18:29Z","timestamp":1759364309527,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032027245","type":"print"},{"value":"9783032027252","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-02725-2_23","type":"book-chapter","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:50:59Z","timestamp":1759279859000},"page":"299-309","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Domain Adaptation of\u00a0the\u00a0Whisper ASR Model for\u00a0Tourism Call Center Transcription in\u00a0Polish"],"prefix":"10.1007","author":[{"given":"Maria","family":"Bollin","sequence":"first","affiliation":[]},{"given":"Wojciech","family":"Meler","sequence":"additional","affiliation":[]},{"given":"Jan","family":"Piesiewicz","sequence":"additional","affiliation":[]},{"given":"\u0141ukasz","family":"Ra\u0327balski","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,1]]},"reference":[{"key":"23_CR1","unstructured":"Ardila, R., et al: Common voice: a massively-multilingual speech corpus (2020)"},{"key":"23_CR2","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/S10994-009-5152-4","volume":"79","author":"S Ben-David","year":"2010","unstructured":"Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., Wortman Vaughan, J.: A theory of learning from different domains. Mach. Learn. 79, 151\u2013175 (2010). https:\/\/doi.org\/10.1007\/S10994-009-5152-4","journal-title":"Mach. Learn."},{"key":"23_CR3","doi-asserted-by":"publisher","unstructured":"Borgholt, L., Havtorn, J., Agi\u0107., S\u00f8gaard, A., Maal\u00f8e, L., Igel, C.: Do end-to-end speech recognition models care about context? In: Interspeech 2020, pp. 4352\u20134356 (2020). https:\/\/doi.org\/10.21437\/Interspeech.2020-1750","DOI":"10.21437\/Interspeech.2020-1750"},{"key":"23_CR4","doi-asserted-by":"publisher","unstructured":"Chan, W., Jaitly, N., Le, Q., Vinyals, O.: Listen, attend and spell: a neural network for large vocabulary conversational speech recognition. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4960\u20134964 (2016). https:\/\/doi.org\/10.1109\/ICASSP.2016.7472621","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"23_CR5","unstructured":"Conneau, A., et al.: Fleurs: Few-shot learning evaluation of universal representations of speech (2022). https:\/\/arxiv.org\/abs\/2205.12446, arXiv preprint, arXiv:2205.12446"},{"key":"23_CR6","doi-asserted-by":"publisher","unstructured":"Furui, S.: 50 years of progress in speech and speaker recognition research. 1(2), 64\u201374 (1970). https:\/\/doi.org\/10.37936\/ECTI-CIT.200512.51834","DOI":"10.37936\/ECTI-CIT.200512.51834"},{"key":"23_CR7","doi-asserted-by":"publisher","unstructured":"Graves, A.: Sequence transduction with recurrent neural networks (2012). https:\/\/doi.org\/10.48550\/arXiv.1211.3711, arXiv preprint, arXiv:1211.3711","DOI":"10.48550\/arXiv.1211.3711"},{"issue":"6","key":"23_CR8","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82\u201397 (2012). https:\/\/doi.org\/10.1109\/MSP.2012.2205597","journal-title":"IEEE Signal Process. Mag."},{"key":"23_CR9","doi-asserted-by":"publisher","unstructured":"Junczyk, M.: Bigos - benchmark intended grouping of open speech corpora for polish automatic speech recognition. In: Proceedings of the 18th Conference on Computer Science and Intelligence Systems (FedCSIS), pp. 585\u2013590 (2023). https:\/\/doi.org\/10.15439\/2023F1609","DOI":"10.15439\/2023F1609"},{"key":"23_CR10","doi-asserted-by":"publisher","unstructured":"Junczyk, M.: Framework for curating speech datasets and evaluating ASR systems: a case study for polish (2024). https:\/\/doi.org\/10.48550\/arXiv.2408.00005, arXiv preprint, arXiv:2408.00005","DOI":"10.48550\/arXiv.2408.00005"},{"key":"23_CR11","doi-asserted-by":"publisher","unstructured":"Kim, H.K., Rose, R.C.: Speech recognition over mobile networks. In: Automatic Speech Recognition on Mobile Devices and over Communication Networks. Advances in Pattern Recognition, pp. 41\u201361. Springer, London (2008). https:\/\/doi.org\/10.1007\/978-1-84800-143-5_3","DOI":"10.1007\/978-1-84800-143-5_3"},{"key":"23_CR12","doi-asserted-by":"publisher","unstructured":"Meyer, J., Dentel, L., Meunier, F.: Speech recognition in natural background noise. PLOS ONE 8 (2013). https:\/\/doi.org\/10.1371\/JOURNAL.PONE.0079279","DOI":"10.1371\/JOURNAL.PONE.0079279"},{"key":"23_CR13","doi-asserted-by":"publisher","unstructured":"Park, D.S., et al.: Specaugment: a simple data augmentation method for automatic speech recognition. In: Interspeech 2019. ISCA (2019). https:\/\/doi.org\/10.21437\/interspeech.2019-2680","DOI":"10.21437\/interspeech.2019-2680"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Pondel-Sycz, K., Bilski, P.: System dedicated to polish automatic speech recognition - overview of solutions. Bull. Pol. Acad. Sci. Tech. Sci. 72(4) (2024). https:\/\/doi.org\/10.24425\/bpasts.2024.149818","DOI":"10.24425\/bpasts.2024.149818"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Pratap, V., Xu, Q., Sriram, A., Synnaeve, G., Collobert, R.: Mls: a large-scale multilingual dataset for speech research (2020). arXiv preprint, arXiv:2012.03411","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"23_CR16","doi-asserted-by":"publisher","unstructured":"P\u0229zik, P., Junczyk, M.: pl-asr-pelcra-for-bigos (revision 4205ec7) (2024). https:\/\/doi.org\/10.57967\/hf\/2387. https:\/\/huggingface.co\/datasets\/pelcra\/pl-asr-pelcra-for-bigos. hugging Face","DOI":"10.57967\/hf\/2387"},{"key":"23_CR17","unstructured":"P\u0229zik, P., et al.: Diabiz \u2013 an annotated corpus of polish call center dialogs. In: Proceedings of the Thirteenth Language Resources and Evaluation Conference, pp. 723\u2013726. European Language Resources Association (2022). https:\/\/aclanthology.org\/2022.lrec-1.76\/"},{"key":"23_CR18","doi-asserted-by":"publisher","first-page":"44580","DOI":"10.1109\/ACCESS.2021.3066801","volume":"9","author":"M P\u0142aza","year":"2021","unstructured":"P\u0142aza, M., Pawlik, L.: Influence of the contact center systems development on key performance indicators. IEEE Access 9, 44580\u201344591 (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3066801","journal-title":"IEEE Access"},{"key":"23_CR19","doi-asserted-by":"publisher","unstructured":"Radford, A., Kim, J., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision (2022). https:\/\/doi.org\/10.48550\/arXiv.2212.04356, arXiv preprint, arXiv:2212.04356","DOI":"10.48550\/arXiv.2212.04356"},{"key":"23_CR20","unstructured":"Rupali, M., Sable, G.: An overview of speech recognition using hmm. In: Lecture Notes in Computer Science, pp. 233\u2013238 (2013)"},{"key":"23_CR21","unstructured":"SileroTeam: Silero vad: pre-trained enterprise-grade voice activity detector (vad), number detector and language classifier (2024). https:\/\/github.com\/snakers4\/silero-vad"},{"key":"23_CR22","unstructured":"Thuestad, J., Grutle, O.: Speech-to-text models to transcribe emergency calls. Master\u2019s thesis, University of Bergen (2023). https:\/\/hdl.handle.net\/11250\/3083251, master\u2019s thesis, University of Bergen, Bergen, Norway"}],"container-title":["Lecture Notes in Computer Science","Advances in Computational Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-02725-2_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:51:04Z","timestamp":1759279864000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-02725-2_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,1]]},"ISBN":["9783032027245","9783032027252"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-02725-2_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,1]]},"assertion":[{"value":"1 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IWANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Work-Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"A Coru\u00f1a","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwann2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iwann.uma.es\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}