Open Set Audio Classification Using Autoencoders Trained on Few Data

Naranjo-Alcazar, Javier; Perez-Castanos, Sergi; Zuccarello, Pedro; Antonacci, Fabio; Cobos, Máximo

doi:10.3390/s20133741

Cited by 12 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The problem of open-set recognition coupled with few-shot learning is also faced in Ref. [42]. Two different autoencoder architectures with a multi-layer perceptron classifier are designed to identify target sound classes and reject unwanted ones.…”

Section: Related Workmentioning

confidence: 99%

Few-Shot Emergency Siren Detection

Cantarini

Gabrielli

Squartini

2022

Sensors

View full text Add to dashboard Cite

It is a well-established practice to build a robust system for sound event detection by training supervised deep learning models on large datasets, but audio data collection and labeling are often challenging and require large amounts of effort. This paper proposes a workflow based on few-shot metric learning for emergency siren detection performed in steps: prototypical networks are trained on publicly available sources or synthetic data in multiple combinations, and at inference time, the best knowledge learned in associating a sound with its class representation is transferred to identify ambulance sirens, given only a few instances for the prototype computation. Performance is evaluated on siren recordings acquired by sensors inside and outside the cabin of an equipped car, investigating the contribution of filtering techniques for background noise reduction. The results show the effectiveness of the proposed approach, achieving AUPRC scores equal to 0.86 and 0.91 in unfiltered and filtered conditions, respectively, outperforming a convolutional baseline model with and without fine-tuning for domain adaptation. Extensive experiments conducted on several recording sensor placements prove that few-shot learning is a reliable technique even in real-world scenarios and gives valuable insights for developing an in-car emergency vehicle detection system.

show abstract

Section: Related Workmentioning

confidence: 99%

Few-Shot Emergency Siren Detection

Cantarini

Gabrielli

Squartini

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Auto-Encoders [13, 14] learn a compact latent representation of an input sample and are trained using a reconstruction loss. Using regularizations and constraints, the latent space can be adjusted for various tasks, such as classification [15]. However, the learned features remain largely non-interpretable and abstract.…”

Section: Related Workmentioning

confidence: 99%

A Model You Can Hear: Audio Identification with Playable Prototypes

Loiseau

Bouvier²,

Teytaut³

et al. 2022

Preprint

View full text Add to dashboard Cite

Machine learning techniques have proved useful for classifying and analyzing audio content. However, recent methods typically rely on abstract and high-dimensional representations that are difficult to interpret. Inspired by transformation-invariant approaches developed for image and 3D data, we propose an audio identification model based on learnable spectral prototypes. Equipped with dedicated transformation networks, these prototypes can be used to cluster and classify input audio samples from large collections of sounds. Our model can be trained with or without supervision and reaches state-ofthe-art results for speaker and instrument identification, while remaining easily interpretable. The code is available at: https://github.com/romainloiseau/ a-model-you-can-hear

show abstract

“…Although audio signals are natively one-dimensional sequences, most state-of-the-art approaches to audio classification based on CNNs use a two-dimensional (2D) input [12,13]. Usually, these 2D inputs computed from the audio signal are well-known time-frequency representations such as Mel-spectrograms [14,15,16,17] or the output of constant-Q transform [18] (CQT) filterbanks, among others. Time-frequency 2D audio representations are able to accurately extract acoustically meaningful patterns but require a set of parameters to be specified, such as the window type and length, hop size or the number of frequency bins.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Analysis of Residual Block Alternatives for End-to-End Audio Classification

Naranjo-Alcazar

Perez-Castanos²,

Martín-Morató

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Residual learning is known for being a learning framework that facilitates the training of very deep neural networks. Residual blocks or units are made up of a set of stacked layers, where the inputs are added back to their outputs with the aim of creating identity mappings. In practice, such identity mappings are accomplished by means of the so-called skip or shortcut connections. However, multiple implementation alternatives arise with respect to where such skip connections are applied within the set of stacked layers making up a residual block. While residual networks for image classification using convolutional neural networks (CNNs) have been widely discussed in the literature, their adoption for 1D end-to-end architectures is still scarce in the audio domain. Thus, the suitability of different residual block designs for raw audio classification is partly unknown. The purpose of this paper is to compare, analyze and discuss the performance of several residual block implementations, the most commonly used in image classification problems, within a state-of-the-art CNN-based architecture for end-to-end audio classification using raw audio waveforms. Deep and careful statistical analyses over six different residual block alternatives are conducted, considering two well-known datasets and common input normalization choices. The results show that, while some significant differences in performance are observed among architectures using different residual block designs, the selection of the most suitable residual block can be highly dependent on the input data.

show abstract

Open Set Audio Classification Using Autoencoders Trained on Few Data

Cited by 12 publications

References 35 publications

Few-Shot Emergency Siren Detection

Few-Shot Emergency Siren Detection

A Model You Can Hear: Audio Identification with Playable Prototypes

A Comparative Analysis of Residual Block Alternatives for End-to-End Audio Classification

Contact Info

Product

Resources

About