Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen:
https://doi.org/10.21256/zhaw-20125
Publikationstyp: | Konferenz: Paper |
Art der Begutachtung: | Peer review (Publikation) |
Titel: | CEASR : a corpus for evaluating automatic speech recognition |
Autor/-in: | Ulasik, Malgorzata Anna Hürlimann, Manuela Germann, Fabian Gedik, Esin Benites de Azevedo e Souza, Fernando Cieliebak, Mark |
et. al: | No |
DOI: | 10.21256/zhaw-20125 |
Tagungsband: | Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020) |
Herausgeber/-in des übergeordneten Werkes: | Calzolari, Nicoletta Béchet, Frédéric Blache, Philippe Choukri, Khalid Cieri, Christopher Declerck, Thierry Goggi, Sara Isahara, Hitoshi Maegaard, Bente Mariani, Joseph Mazo, Hélène Moreno, Asuncion Odijk, Jan Piperidis, Stelios |
Seite(n): | 6477 |
Seiten bis: | 6485 |
Angaben zur Konferenz: | 12th Language Resources and Evaluation Conference (LREC), Marseille, France, 11-16 May 2020 |
Erscheinungsdatum: | 2020 |
Verlag / Hrsg. Institution: | European Language Resources Association |
ISBN: | 979-10-95546-34-4 |
Sprache: | Englisch |
Schlagwörter: | Automatic speech recognition; Evaluation; Speech corpus; ASR system |
Fachgebiet (DDC): | 006: Spezielle Computerverfahren |
Zusammenfassung: | In this paper, we present CEASR, a Corpus for Evaluating ASR quality. It is a data set derived from public speech corpora, containing manual transcripts enriched with metadata along with transcripts generated by several modern state-of-the-art ASR systems. CEASR provides this data in a unified structure, consistent across all corpora and systems with normalised transcript texts and metadata. We then use CEASR to evaluate the quality of ASR systems on the basis of their Word Error Rate (WER). Our experiments show, among other results, a substantial difference in quality between commercial versus open-source ASR tools and differences up to a factor of ten for single systems on different corpora. By using CEASR, we could very efficiently and easily obtain these results. This shows that our corpus enables researchers to perform ASR-related evaluations and various in-depth analyses with noticeably reduced effort: without the need to collect, process and transcribe the speech data themselves. |
URI: | https://www.aclweb.org/anthology/2020.lrec-1.798 https://digitalcollection.zhaw.ch/handle/11475/20125 |
Volltext Version: | Publizierte Version |
Lizenz (gemäss Verlagsvertrag): | CC BY-NC 4.0: Namensnennung - Nicht kommerziell 4.0 International |
Departement: | School of Engineering |
Organisationseinheit: | Institut für Informatik (InIT) |
Enthalten in den Sammlungen: | Publikationen School of Engineering |
Dateien zu dieser Ressource:
Datei | Beschreibung | Größe | Format | |
---|---|---|---|---|
2020_Ulasik-etal_CEASR_LREC.pdf | 733.4 kB | Adobe PDF | Öffnen/Anzeigen |
Zur Langanzeige
Ulasik, M. A., Hürlimann, M., Germann, F., Gedik, E., Benites de Azevedo e Souza, F., & Cieliebak, M. (2020). CEASR : a corpus for evaluating automatic speech recognition [Conference paper]. In N. Calzolari, F. Béchet, P. Blache, K. Choukri, C. Cieri, T. Declerck, S. Goggi, H. Isahara, B. Maegaard, J. Mariani, H. Mazo, A. Moreno, J. Odijk, & S. Piperidis (Eds.), Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020) (pp. 6477–6485). European Language Resources Association. https://doi.org/10.21256/zhaw-20125
Ulasik, M.A. et al. (2020) ‘CEASR : a corpus for evaluating automatic speech recognition’, in N. Calzolari et al. (eds) Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020). European Language Resources Association, pp. 6477–6485. Available at: https://doi.org/10.21256/zhaw-20125.
M. A. Ulasik, M. Hürlimann, F. Germann, E. Gedik, F. Benites de Azevedo e Souza, and M. Cieliebak, “CEASR : a corpus for evaluating automatic speech recognition,” in Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), 2020, pp. 6477–6485. doi: 10.21256/zhaw-20125.
ULASIK, Malgorzata Anna, Manuela HÜRLIMANN, Fabian GERMANN, Esin GEDIK, Fernando BENITES DE AZEVEDO E SOUZA und Mark CIELIEBAK, 2020. CEASR : a corpus for evaluating automatic speech recognition. In: Nicoletta CALZOLARI, Frédéric BÉCHET, Philippe BLACHE, Khalid CHOUKRI, Christopher CIERI, Thierry DECLERCK, Sara GOGGI, Hitoshi ISAHARA, Bente MAEGAARD, Joseph MARIANI, Hélène MAZO, Asuncion MORENO, Jan ODIJK und Stelios PIPERIDIS (Hrsg.), Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020) [online]. Conference paper. European Language Resources Association. 2020. S. 6477–6485. ISBN 979-10-95546-34-4. Verfügbar unter: https://www.aclweb.org/anthology/2020.lrec-1.798
Ulasik, Malgorzata Anna, Manuela Hürlimann, Fabian Germann, Esin Gedik, Fernando Benites de Azevedo e Souza, and Mark Cieliebak. 2020. “CEASR : A Corpus for Evaluating Automatic Speech Recognition.” Conference paper. In Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), edited by Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, et al., 6477–85. European Language Resources Association. https://doi.org/10.21256/zhaw-20125.
Ulasik, Malgorzata Anna, et al. “CEASR : A Corpus for Evaluating Automatic Speech Recognition.” Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), edited by Nicoletta Calzolari et al., European Language Resources Association, 2020, pp. 6477–85, https://doi.org/10.21256/zhaw-20125.
Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.