{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T18:21:41Z","timestamp":1775845301823,"version":"3.50.1"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031779602","type":"print"},{"value":"9783031779619","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-77961-9_6","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T13:54:32Z","timestamp":1732197272000},"page":"82-91","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Benchmarking Whisper Under Diverse Audio Transformations and\u00a0Real-Time Constraints"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1000-295X","authenticated-orcid":false,"given":"Sergei","family":"Katkov","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2773-4421","authenticated-orcid":false,"given":"Antonio","family":"Liotta","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4166-540X","authenticated-orcid":false,"given":"Alessandro","family":"Vietti","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"6_CR1","doi-asserted-by":"publisher","unstructured":"Adolfi, F., Bowers, J.S., Poeppel, D.: Successes and critical failures of neural networks in capturing human-like speech recognition. Neural Netw. 162(C), 199\u2013211 (2023). https:\/\/doi.org\/10.1016\/j.neunet.2023.02.032","DOI":"10.1016\/j.neunet.2023.02.032"},{"key":"6_CR2","unstructured":"Ardila, R., et al.: Common voice: A massively-multilingual speech corpus. In: International Conference on Language Resources and Evaluation (2019). https:\/\/api.semanticscholar.org\/CorpusID:209376338"},{"key":"6_CR3","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":"6_CR4","unstructured":"Cui, T., Xiao, J., Li, L., Jiang, X., Liu, Q.: An approach to improve robustness of NLP systems against ASR errors. ArXiv abs\/2103.13610 (2021). https:\/\/api.semanticscholar.org\/CorpusID:232352551"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Duarte, J.C., Colcher, S.: Building a noisy audio dataset to evaluate machine learning approaches for automatic speech recognition systems. ArXiv abs\/2110.01425 (2018). https:\/\/api.semanticscholar.org\/CorpusID:238259030","DOI":"10.17771\/PUCRio.DImcc.60957"},{"key":"6_CR6","doi-asserted-by":"publisher","unstructured":"Everson, K., et al.: Towards ASR robust spoken language understanding through in-context learning with word confusion networks. In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 12856\u201312860 (2024). https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10447938","DOI":"10.1109\/ICASSP48485.2024.10447938"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Gulati, A., et al. (eds.): Conformer: Convolution-augmented Transformer for Speech Recognition (2020)","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"6_CR8","doi-asserted-by":"publisher","unstructured":"Higuchi, Y., Tawara, N., Ogawa, A., Iwata, T., Kobayashi, T., Ogawa, T.: Noise-robust attention learning for end-to-end speech recognition. In: 2020 28th European Signal Processing Conference (EUSIPCO), pp 311\u2013315 (2021). https:\/\/doi.org\/10.23919\/Eusipco47968.2020.9287488","DOI":"10.23919\/Eusipco47968.2020.9287488"},{"key":"6_CR9","unstructured":"Katkov, S., Liotta, A., Vietti, A.: Robustness of ASR systems in multilingual and acoustically challenging environments. In: Proceedings of the 23rd International Conference of the Italian Association for Artificial Intelligence (AIxIA) (2024)"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Mach\u00e1\u010dek, D., Dabre, R., Bojar, O.: Turning whisper into real-time transcription system. In: Saha, S., Sujaini, H. (eds.) Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations, 17\u201324. Association for Computational Linguistics, Bali, Indonesia (2023).https:\/\/aclanthology.org\/2023.ijcnlp-demo.3","DOI":"10.18653\/v1\/2023.ijcnlp-demo.3"},{"key":"6_CR11","unstructured":"Mauch, M., Ewert, S.: The audio degradation toolbox and its application to robustness evaluation. In: International Society for Music Information Retrieval Conference (2013). https:\/\/api.semanticscholar.org\/CorpusID:11675708"},{"key":"6_CR12","doi-asserted-by":"publisher","unstructured":"M\u00fcller, J.A., Wendt, D., Kollmeier, B., Debener, S., Brand, T.: Effect of speech rate on neural tracking of speech. Front. Psychol. 10 (2019). https:\/\/doi.org\/10.3389\/fpsyg.2019.00449, https:\/\/www.frontiersin.org\/journals\/psychology\/articles\/10.3389\/fpsyg.2019.00449","DOI":"10.3389\/fpsyg.2019.00449"},{"key":"6_CR13","doi-asserted-by":"publisher","unstructured":"N\u00e1b\u011blek, A.K., Robinson, P.K.: Monaural and binaural speech perception in reverberation for listeners of various ages. J. Acoust. Soc. Am. 71(5), 1242\u20131248 (1982). https:\/\/doi.org\/10.1121\/1.387773","DOI":"10.1121\/1.387773"},{"key":"6_CR14","doi-asserted-by":"publisher","unstructured":"Payton, K.L., Uchanski, R.M., Braida, L.D.: Intelligibility of conversational and clear speech in noise and reverberation for listeners with normal and impaired hearing. J. Acoust. Soc. Am. 95(3), 1581\u20131592 (1994). https:\/\/doi.org\/10.1121\/1.408545","DOI":"10.1121\/1.408545"},{"key":"6_CR15","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., Mcleavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., Scarlett, J. (eds.) Proceedings of the 40th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0202, pp. 28492\u201328518. PMLR (23\u201329 Jul 2023) (2023). https:\/\/proceedings.mlr.press\/v202\/radford23a.html"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-77961-9_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T14:04:15Z","timestamp":1732197855000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-77961-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031779602","9783031779619"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-77961-9_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgrade","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Serbia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom2024.ftn.uns.ac.rs\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}