{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T01:34:54Z","timestamp":1755221694209,"version":"3.43.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031834318"},{"type":"electronic","value":"9783031834325"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-83432-5_20","type":"book-chapter","created":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T04:15:59Z","timestamp":1741061759000},"page":"285-299","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Comparative Evaluation of Speech-to-Text Software Based on Sociodemographic and Environmental Factors"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7530-9753","authenticated-orcid":false,"given":"Jorge","family":"Morato","sequence":"first","affiliation":[]},{"given":"Alejandro","family":"Pedrero","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7722-1982","authenticated-orcid":false,"given":"Sonia","family":"Sanchez-Cuadrado","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,5]]},"reference":[{"key":"20_CR1","doi-asserted-by":"publisher","unstructured":"Deng, L., Liu, Y. eds: Deep Learning in Natural Language Processing. Springer Singapore, Singapore (2018). https:\/\/doi.org\/10.1007\/978-981-10-5209-5","DOI":"10.1007\/978-981-10-5209-5"},{"key":"20_CR2","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1186\/s13636-022-00251-w","volume":"2022","author":"V Roger","year":"2022","unstructured":"Roger, V., Farinas, J., Pinquier, J.: Deep neural networks for automatic speech processing: a survey from large corpora to limited data. J. Audio Speech Music Proc. 2022, 19 (2022). https:\/\/doi.org\/10.1186\/s13636-022-00251-w","journal-title":"J. Audio Speech Music Proc."},{"key":"20_CR3","unstructured":"Richter, F.: Infographic: Smart Speaker Adoption Continues to Rise [Infographic]. Statista Daily Data (2020). https:\/\/www.statista.com\/chart\/16597\/smart-speaker-ownership-in-the-united-states"},{"key":"20_CR4","doi-asserted-by":"publisher","first-page":"8465","DOI":"10.3390\/su13158465","volume":"13","author":"J Morato","year":"2021","unstructured":"Morato, J., Sanchez-Cuadrado, S., Iglesias, A., Campillo, A., Fern\u00e1ndez-Panadero, C.: Sustainable technologies for older adults. Sustainability 13, 8465 (2021). https:\/\/doi.org\/10.3390\/su13158465","journal-title":"Sustainability"},{"key":"20_CR5","unstructured":"Kashinath, G., Kanhaiya, K., Vineet, K.: Speech-to-Text API Market. Allied Market Research, report code A09527 (2023)"},{"key":"20_CR6","doi-asserted-by":"publisher","unstructured":"Yu, D., Deng, L.: Automatic Speech Recognition: A Deep Learning Approach. Springer London, London (2015). https:\/\/doi.org\/10.1007\/978-1-4471-5779-3","DOI":"10.1007\/978-1-4471-5779-3"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Watanabe, S., Delcroix, M., Metze, F., Hershey, J.R. eds: New Era for Robust Speech Recognition: Exploiting Deep Learning. Springer International Publishing: Imprint: Springer, Cham (2017)","DOI":"10.1007\/978-3-319-64680-0"},{"key":"20_CR8","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436\u2013444 (2015). https:\/\/doi.org\/10.1038\/nature14539","journal-title":"Nature"},{"key":"20_CR9","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.procs.2018.03.005","volume":"128","author":"R Errattahi","year":"2018","unstructured":"Errattahi, R., El Hannani, A., Ouahmane, H.: Automatic speech recognition errors detection and correction: a review. Procedia Comput. Sci. 128, 32\u201337 (2018). https:\/\/doi.org\/10.1016\/j.procs.2018.03.005","journal-title":"Procedia Comput. Sci."},{"key":"20_CR10","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1016\/j.csi.2012.09.004","volume":"35","author":"M Marrero","year":"2013","unstructured":"Marrero, M., Urbano, J., S\u00e1nchez-Cuadrado, S., Morato, J., G\u00f3mez-Berb\u00eds, J.M.: Named entity recognition: fallacies, challenges and opportunities. Comput. Stand. Interfaces 35, 482\u2013489 (2013). https:\/\/doi.org\/10.1016\/j.csi.2012.09.004","journal-title":"Comput. Stand. Interfaces"},{"key":"20_CR11","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2021.702739","volume":"13","author":"LE Humes","year":"2021","unstructured":"Humes, L.E.: Factors underlying individual differences in speech-recognition threshold (SRT) in noise among older adults. Front. Aging Neurosci. 13, 702739 (2021). https:\/\/doi.org\/10.3389\/fnagi.2021.702739","journal-title":"Front. Aging Neurosci."},{"key":"20_CR12","unstructured":"Ogun, S.: How to create a speech dataset for ASR, TTS, and other speech tasks [Blog] (2021). https:\/\/ogunlao.github.io\/blog\/2021\/01\/26\/how-to-create-speech-dataset.html"},{"key":"20_CR13","doi-asserted-by":"publisher","unstructured":"Tatman, R., Kasten, C.: Effects of talker dialect, gender & race on accuracy of Bing speech and Youtube automatic captions. In: Interspeech 2017, pp. 934\u2013938. ISCA (2017). https:\/\/doi.org\/10.21437\/Interspeech.2017-1746","DOI":"10.21437\/Interspeech.2017-1746"},{"key":"20_CR14","doi-asserted-by":"publisher","unstructured":"Winata, G.I., et al.: Learning fast adaptation on cross-accented speech recognition. In: Interspeech 2020, pp. 1276\u20131280. ISCA (2020). https:\/\/doi.org\/10.21437\/Interspeech.2020-45","DOI":"10.21437\/Interspeech.2020-45"},{"key":"20_CR15","doi-asserted-by":"publisher","unstructured":"Lu, X., Li, S., Fujimoto, M.: Automatic Speech Recognition. In: Kidawara, Y., Sumita, E., Kawai, H. (eds.) Speech-to-Speech Translation, pp. 21\u201338. Springer Singapore, Singapore (2020). https:\/\/doi.org\/10.1007\/978-981-15-0595-9_2","DOI":"10.1007\/978-981-15-0595-9_2"},{"key":"20_CR16","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1080\/13645579.2022.2087849","volume":"26","author":"SJ Pentland","year":"2023","unstructured":"Pentland, S.J., Fuller, C.M., Spitzley, L.A., Twitchell, D.P.: Does accuracy matter? Methodological considerations when using automated speech-to-text for social science research. Int. J. Soc. Res. Methodol. 26, 661\u2013677 (2023). https:\/\/doi.org\/10.1080\/13645579.2022.2087849","journal-title":"Int. J. Soc. Res. Methodol."},{"key":"20_CR17","doi-asserted-by":"publisher","first-page":"7621","DOI":"10.3758\/s13428-024-02440-1","volume":"56","author":"VA Pfeifer","year":"2024","unstructured":"Pfeifer, V.A., Chilton, T.D., Grilli, M.D., Mehl, M.R.: How ready is speech-to-text for psychological language research? Evaluating the validity of AI-generated English transcripts for analyzing free-spoken responses in younger and older adults. Behav. Res. 56, 7621\u20137631 (2024). https:\/\/doi.org\/10.3758\/s13428-024-02440-1","journal-title":"Behav. Res."},{"key":"20_CR18","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/S0167-6393(01)00041-3","volume":"38","author":"D Klakow","year":"2002","unstructured":"Klakow, D., Peters, J.: Testing the correlation of word error rate and perplexity. Speech Commun. 38, 19\u201328 (2002). https:\/\/doi.org\/10.1016\/S0167-6393(01)00041-3","journal-title":"Speech Commun."},{"key":"20_CR19","doi-asserted-by":"publisher","unstructured":"Durand, J.: Corpus Phonology. In: Oxford Research Encyclopedia of Linguistics. Oxford University Press (2017). https:\/\/doi.org\/10.1093\/acrefore\/9780199384655.013.145","DOI":"10.1093\/acrefore\/9780199384655.013.145"},{"key":"20_CR20","doi-asserted-by":"publisher","unstructured":"Niemants, N.: Des enregistrements aux corpus: transcription et extraction de donn\u00e9es d\u2019interpr\u00e9tation en milieu m\u00e9dical. meta. 63, 665\u2013694 (2019). https:\/\/doi.org\/10.7202\/1060168ar","DOI":"10.7202\/1060168ar"},{"key":"20_CR21","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1109\/TETCI.2017.2762739","volume":"2","author":"M Ravanelli","year":"2018","unstructured":"Ravanelli, M., Brakel, P., Omologo, M., Bengio, Y.: Light gated recurrent units for speech recognition. IEEE Trans. Emerg. Top. Comput. Intell. 2, 92\u2013102 (2018). https:\/\/doi.org\/10.1109\/TETCI.2017.2762739","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"20_CR22","first-page":"6","volume":"107","author":"G Dias","year":"2020","unstructured":"Dias, G.: Dossier: IA & technologies du langage humain. Bulletin de l\u2019AFIA 107, 6\u20139 (2020)","journal-title":"Bulletin de l\u2019AFIA"},{"key":"20_CR23","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1093\/jamia\/ocy179","volume":"26","author":"SV Blackley","year":"2019","unstructured":"Blackley, S.V., Huynh, J., Wang, L., Korach, Z., Zhou, L.: Speech recognition for clinical documentation from 1990 to 2018: a systematic review. J. Am. Med. Inform. Assoc. 26, 324\u2013338 (2019). https:\/\/doi.org\/10.1093\/jamia\/ocy179","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Iancu, B.: Evaluating Google Speech-to-Text API's performance for Romanian e-learning resources. Informatica Economica 23(1), 17\u201325 (2019). https:\/\/ideas.repec.org\/a\/aes\/infoec\/v23y2019i1p17-25.html","DOI":"10.12948\/issn14531305\/23.1.2019.02"},{"key":"20_CR25","doi-asserted-by":"publisher","unstructured":"Rufino Morales, M.: Estudio comparativo de m\u00e9todos de transcripci\u00f3n para corpus orales: el caso del espa\u00f1ol. Revista Nebrija de Ling\u00fc\u00edstica Aplicada a la Ense\u00f1anza de Lenguas 14, 126\u2013146 (2020). https:\/\/doi.org\/10.26378\/rnlael1429406","DOI":"10.26378\/rnlael1429406"},{"key":"20_CR26","doi-asserted-by":"publisher","unstructured":"Serna, Y., Morato, J, Sanchez-Cuadrado, S.: Evaluaci\u00f3n de la comprensi\u00f3n de los paneles interpretativos en parajes naturales. Scire 24, 53\u201362 (2018). https:\/\/doi.org\/10.54886\/scire.v24i2.4568","DOI":"10.54886\/scire.v24i2.4568"}],"container-title":["Communications in Computer and Information Science","Advanced Research in Technologies, Information, Innovation and Sustainability"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-83432-5_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,9]],"date-time":"2025-08-09T08:04:19Z","timestamp":1754726659000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-83432-5_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031834318","9783031834325"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-83432-5_20","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"5 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ARTIIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Research in Technologies, Information, Innovation and Sustainability","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Santiago de Chile","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chile","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":"20 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"artiis2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.artiis.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}