Abstract
The determination of an article for gender assignment to a noun is different in every language and depends on the certain rules as well as the context of a word in a text. The rules given in the German language help with the article assignment, but are not always consistent and meaningful for all words. In the human brain, this assignment can take place intuitively and in real-time, if it is trained over many years. This work is concerned with verifying whether a convolutional neural network (CNN) can match an article to a word the same way as the human brain, using methods of audio classification in deep learning. The chosen attribute to train the model is the sound of the word in this work, because the sound plays a big role in the article determination.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Genus bei Fremdwörtern-Variantengrammatik des Standarddeutschen, http://mediawiki.ids-mannheim.de/VarGra/index.php/Genus_bei_ Fremdwörtern, Accessed 31 May 2022
Doshi, K.: Audio deep learning made simple: sound classification, step-by-step by Ketan Doshi towards data science. https://towardsdatascience.com/audio-deep-learning-made-simple-sound-classification-step-by-step-cebc936bbe5. Accessed 15 May 2022
Yang, Y. -Y., et al.: Torchaudio: building blocks for audio and speech processing. In: ICASSP 2022–2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6982–6986 (2022). https://doi.org/10.1109/ICASSP43922.2022.9747236
McFee, B., et al.: librosa: audio and music signal analysis in python. In: Proceedings of the 14th python in Science Conference, pp. 18–25 (2015). https://doi.org/10.5281/zenodo.4792298
[at] REDAKTION. Convolutional Neural Networks [at] Blog. https://www.alexanderthamm.com/de/blog/convolutional-neural-networks-am-beispiel-der-revolution-der-computervision/. Accessed 31 May 2022
Allibhai, E.: Hold-out vs. cross-validation in machine learning—by Eijaz Allibhai—medium, https://medium.com/@eijaz/holdout-vs-cross-validation-in-machine-learning-7637112d3f8f. Accessed 10 Apr 2022
How to implement early stop** in PyTorch - Quora, https://www.quora.com/How-can-I-implement-early-stop**-in-PyTorch. Accessed 15 Mar 2022
Logan, B.: Mel Frequency Ceptral Coefficient for Music Modeling. Cambridge Research Laboratory, Cambridge (2000)
Brownlee, J.: Gentle Introduction to the Adam Optimization Algorithm for Deep Learning. Machine Learning Mastery, San Juan, Blog (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zaiss, D., Gilani, I.B.M., Tutsch, D. (2023). Real-Time Audio Classification to Determine the Article of a German Noun. In: Unger, H., Schaible, M. (eds) Real-time and Autonomous Systems 2022. Real-Time 2022. Lecture Notes in Networks and Systems, vol 674. Springer, Cham. https://doi.org/10.1007/978-3-031-32700-1_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-32700-1_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-32699-8
Online ISBN: 978-3-031-32700-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)