Hauptthemen unserer Publikationen zu Schweizerdeutsch:
2022
Proceedings Articles
Plüss, Michel; Hürlimann, Manuela; Cuny, Marc; Stockli, Alla; Kapotis, Nikolaos; Hartmann, Julia; Ulasik, Malgorzata Anna; Scheller, Christian; Schraner, Yanick; Jain, Amit; Deriu, Jan; Cieliebak, Mark; Vogel, Manfred
SDS-200: A Swiss German Speech to Standard German Text Corpus Proceedings Article
In: 13th International Conference on Language Resources,; (LREC), Evaluation (Hrsg.): 2022.
Links | BibTeX | Schlagwörter: Corpus, Endangered Languages, Less-Resourced Languages, Speech Recognition/Understanding, Statistical and Machine Learning Methods
@inproceedings{,
title = {SDS-200: A Swiss German Speech to Standard German Text Corpus},
author = {Michel Plüss and Manuela Hürlimann and Marc Cuny and Alla Stockli and Nikolaos Kapotis and Julia Hartmann and Malgorzata Anna Ulasik and Christian Scheller and Yanick Schraner and Amit Jain and Jan Deriu and Mark Cieliebak and Manfred Vogel},
editor = {13th International Conference on Language Resources and Evaluation (LREC)},
url = {http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.347.pdf
https://doi.org/10.48550/arXiv.2205.09501},
doi = {10.48550/arXiv.2205.09501},
year = {2022},
date = {2022-05-19},
urldate = {2022-05-19},
keywords = {Corpus, Endangered Languages, Less-Resourced Languages, Speech Recognition/Understanding, Statistical and Machine Learning Methods},
pubstate = {published},
tppubtype = {inproceedings}
}
Forschungsberichte
Schraner, Yanick; Scheller, Christian; Plüss, Michel; Neukom, Lukas; Vogel, Manfred
Comparison of Unsupervised Learning and Supervised Learning with Noisy Labels for Low-Resource Speech Recognition Forschungsbericht
2022.
Links | BibTeX | Schlagwörter: forced-alignment, low-resource, self-supervised, semi-supervised, Speech Recognition/Understanding, speech translation
@techreport{nokey,
title = {Comparison of Unsupervised Learning and Supervised Learning with Noisy Labels for Low-Resource Speech Recognition},
author = {Yanick Schraner and Christian Scheller and Michel Plüss and Lukas Neukom and Manfred Vogel},
editor = {University of Applied Sciences and Arts Northwestern Switzerland},
url = {https://www.isca-speech.org/archive/pdfs/interspeech_2022/schraner22_interspeech.pdf},
year = {2022},
date = {2022-09-22},
keywords = {forced-alignment, low-resource, self-supervised, semi-supervised, Speech Recognition/Understanding, speech translation},
pubstate = {published},
tppubtype = {techreport}
}
2020
Proceedings Articles
Benites, Fernando; Hürlimann, Manuela; von Däniken, Pius; Cieliebak, Mark
ZHAW-InIT – Social Media Geolocation at VarDial 2020 Proceedings Article
In: on Computational Linguistics (ICCL), International Committee (Hrsg.): S. 254–264, International Committee on Computational Linguistics (ICCL), Barcelona, Spain (Online), 2020.
Abstract | Links | BibTeX | Schlagwörter: Endangered Languages, Geolocation, Less-Resourced Languages, Speech Recognition/Understanding
@inproceedings{nokey,
title = {ZHAW-InIT – Social Media Geolocation at VarDial 2020},
author = {Fernando Benites and Manuela Hürlimann and Pius von Däniken and Mark Cieliebak},
editor = {International Committee on Computational Linguistics (ICCL)},
url = {https://aclanthology.org/2020.vardial-1.24
https://aclanthology.org/2020.vardial-1.24.pdf},
year = {2020},
date = {2020-01-01},
urldate = {2020-01-01},
pages = {254–264},
publisher = {International Committee on Computational Linguistics (ICCL)},
address = {Barcelona, Spain (Online)},
abstract = {We describe our approaches for the Social Media Geolocation (SMG) task at the VarDial Evaluation Campaign 2020. The goal was to predict geographical location (latitudes and longitudes) given an input text. There were three subtasks corresponding to German-speaking Switzerland (CH), Germany and Austria (DE-AT), and Croatia, Bosnia and Herzegovina, Montenegro and Serbia (BCMS). We submitted solutions to all subtasks but focused our development efforts on the CH subtask, where we achieved third place out of 16 submissions with a median distance of 15.93 km and had the best result of 14 unconstrained systems. In the DE-AT subtask, we ranked sixth out of ten submissions (fourth of 8 unconstrained systems) and for BCMS we achieved fourth place out of 13 submissions (second of 11 unconstrained systems).},
keywords = {Endangered Languages, Geolocation, Less-Resourced Languages, Speech Recognition/Understanding},
pubstate = {published},
tppubtype = {inproceedings}
}