SpokeN-100: A Cross-Lingual Benchmarking Dataset for The Classification of Spoken Numbers in Different Languages

Groh R, Goes N, Kist A (2024)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2024

Original Authors: René Groh, Nina Goes, Andreas M. Kist

Event location: Burlingame, CA US

DOI: 10.48550/arXiv.2403.09753

Abstract

Benchmarking plays a pivotal role in assessing and enhancing the performance of compact deep learning models designed for execution on resource-constrained devices, such as microcontrollers. Our study introduces a novel, entirely artificially generated benchmarking dataset tailored for speech recognition, representing a core challenge in the field of tiny deep learning. SpokeN-100 consists of spoken numbers from 0 to 99 spoken by 32 different speakers in four different languages, namely English, Mandarin, German and French, resulting in 12,800 audio samples. We determine auditory features and use UMAP (Uniform Manifold Approximation and Projection for Dimension Reduction) as a dimensionality reduction method to show the diversity and richness of the dataset. To highlight the use case of the dataset, we introduce two benchmark tasks: given an audio sample, classify (i) the used language and/or (ii) the spoken number. We optimized state-of-the-art deep neural networks and performed an evolutionary neural architecture search to find tiny architectures optimized for the 32-bit ARM Cortex-M4 nRF52840 microcontroller. Our results represent the first benchmark data achieved for SpokeN-100.

Authors with CRIS profile

René Groh Juniorprofessur für Artificial Intelligence in Communication Disorders Nina Goes Juniorprofessur für Artificial Intelligence in Communication Disorders Andreas Kist Juniorprofessur für Artificial Intelligence in Communication Disorders

How to cite

APA:

Groh, R., Goes, N., & Kist, A. (2024). SpokeN-100: A Cross-Lingual Benchmarking Dataset for The Classification of Spoken Numbers in Different Languages. In Proceedings of the tinyML Research Symposium 2024. Burlingame, CA, US.

MLA:

Groh, René, Nina Goes, and Andreas Kist. "SpokeN-100: A Cross-Lingual Benchmarking Dataset for The Classification of Spoken Numbers in Different Languages." Proceedings of the tinyML Research Symposium 2024, Burlingame, CA 2024.

BibTeX: Download