Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/81433
Título: | Deep autoencoders for acoustic anomaly detection: experiments with working machine and in-vehicle audio |
Autor(es): | Coelho, Gabriel Matos, Luis Miguel Pereira, Pedro Jose Ferreira, Andre Pilastri, André Luiz Cortez, Paulo |
Palavras-chave: | Acoustic anomaly detection Unsupervised learning Deep autoencoders Industrial and in-vehicle data One-class learning |
Data: | 19-Mai-2022 |
Editora: | Springer |
Revista: | Neural Computing and Applications |
Citação: | Coelho, G., Matos, L.M., Pereira, P.J. et al. Deep autoencoders for acoustic anomaly detection: experiments with working machine and in-vehicle audio. Neural Comput & Applic 34, 19485–19499 (2022). https://doi.org/10.1007/s00521-022-07375-2 |
Resumo(s): | The growing usage of digital microphones has generated an increased interest in the topic of Acoustic Anomaly Detection (AAD). Indeed, there are several real-world AAD application domains, including working machines and in-vehicle intelligence (the main target of this research project). This paper introduces three deep AutoEncoders (AE) for unsupervised AAD tasks, namely a Dense AE, a Convolutional Neural Network (CNN) AE and Long Short-Term Memory Autoencoder (LSTM) AE. To tune the deep learning architectures, development data were adopted from public domain audio datasets related with working machines. A large set of computational experiments was held, showing that the three proposed deep autoencoders, when combined with a melspectrogram sound preprocessing, are quite competitive and outperform a recently proposed AE baseline. Next, on a second experimental stage, aiming to address the final in-vehicle passenger safety goal, the three AEs were adapted to learn from in-vehicle normal audio, assuming three realistic scenarios that were generated by a synthetic audio mixture tool. In general, a high quality AAD discrimination was obtained: working machine data - 72% to 91%; and in-vehicle audio - 78% to 81%. In conjunction with an automotive company, an in-vehicle AAD intelligent system prototype was further developed, aiming to test a selected model (LSTM AE) during a pilot demonstration event that targeted the cough anomaly. Interesting results were obtained, with the AAD system presenting a high cough classification accuracy (e.g., 100% for front seat locations). |
Tipo: | Artigo |
URI: | https://hdl.handle.net/1822/81433 |
DOI: | 10.1007/s00521-022-07375-2 |
ISSN: | 0941-0643 |
Versão da editora: | https://link.springer.com/article/10.1007/s00521-022-07375-2 |
Arbitragem científica: | yes |
Acesso: | Acesso aberto |
Aparece nas coleções: | CAlg - Artigos em revistas internacionais / Papers in international journals |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
aeaad2.pdf | 2,62 MB | Adobe PDF | Ver/Abrir |