The OCON model: an old but green solution for distributable supervised classification for acoustic monitoring in smart cities

TL;DR

This paper presents a simple yet effective One-Class-One-Network model for acoustic classification in smart city environments, achieving competitive accuracy with energy-efficient design suitable for resource-constrained settings.

Contribution

It introduces a structured application of the One-Class approach combined with neural architecture search for acoustic monitoring, demonstrating high accuracy and generalizability in urban speech and pollution detection.

Findings

Achieved classification accuracy comparable to complex architectures.

Demonstrated energy efficiency and generalization in constrained environments.

Provided open-source code for reproducibility.

Abstract

This paper explores a structured application of the One-Class approach and the One-Class-One-Network model for supervised classification tasks, focusing on vowel phonemes classification and speakers recognition for the Automatic Speech Recognition (ASR) domain. For our case-study, the ASR model runs on a proprietary sensing and lightning system, exploited to monitor acoustic and air pollution on urban streets. We formalize combinations of pseudo-Neural Architecture Search and Hyper-Parameters Tuning experiments, using an informed grid-search methodology, to achieve classification accuracy comparable to nowadays most complex architectures, delving into the speaker recognition and energy efficiency aspects. Despite its simplicity, our model proposal has a very good chance to generalize the language and speaker genders context for widespread applicability in computational constrained contexts, proved by relevant statistical and performance metrics. Our experiments code is openly accessible on our GitHub.