Deep Unsupervised Representation Learning for Audio-Based Medical Applications

Amiriparian, Shahin; Schmitt, Maximilian; Ottl, Sandra; Gerczuk, Maurice; Schuller, Björn

doi:10.1007/978-3-030-42750-4_5

Cited by 5 publications

(5 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This toolkit 1 is applied to obtain deep representations from the input audio data utilising image pre-trained Convolutional Neural Networks (CNNs) [1,3]. has been used in previous challenges [25,26] and is described in [3].…”

Section: Deepspectrummentioning

confidence: 99%

The ACM Multimedia 2022 Computational Paralinguistics Challenge

Schuller

Batliner

Amiriparian

et al. 2022

Proceedings of the 30th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Section: Deepspectrummentioning

confidence: 99%

The ACM Multimedia 2022 Computational Paralinguistics Challenge

Schuller

Batliner

Amiriparian

et al. 2022

Proceedings of the 30th ACM International Conference on Multimedia

View full text Add to dashboard Cite

“…Mel-spectrograms of the audio are passed through a pretrained ResNet50 [21] (trained on ImageNet), and the activations of the ‘avg_pool’ layer are extracted, resulting in a 2 048 dimensional feature vector. Deep Spectrum features have been shown to be effective, e. g., for speech processing [46] and audio-based medical applications [47] .…”

Section: The Mask Sub-challenge (Msc)mentioning

confidence: 99%

Face mask recognition from audio: The MASC database and an overview on the mask challenge

Mohamed

Nessiem

Batliner

et al. 2022

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

The sudden outbreak of COVID-19 has resulted in tough challenges for the field of biometrics due to its spread via physical contact, and the regulations of wearing face masks. Given these constraints, voice biometrics can offer a suitable contact-less biometric solution; they can benefit from models that classify whether a speaker is wearing a mask or not. This article reviews the Mask Sub-Challenge (MSC) of the INTERSPEECH 2020 COMputational PARalinguistics challengE (ComParE), which focused on the following classification task: Given an audio chunk of a speaker, classify whether the speaker is wearing a mask or not. First, we report the collection of the Mask Augsburg Speech Corpus (MASC) and the baseline approaches used to solve the problem, achieving a performance of Unweighted Average Recall (UAR). We then summarise the methodologies explored in the submitted and accepted papers that mainly used two common patterns: (i) phonetic-based audio features, or (ii) spectrogram representations of audio combined with Convolutional Neural Networks (CNNs) typically used in image processing. Most approaches enhance their models by adapting ensembles of different models and attempting to increase the size of the training data using various techniques. We review and discuss the results of the participants of this sub-challenge, where the winner scored a UAR of . Moreover, we present the results of fusing the approaches, leading to a UAR of . Finally, we present a smartphone app that can be used as a proof of concept demonstration to detect in real-time whether users are wearing a face mask; we also benchmark the run-time of the best models.

show abstract

“…In this work, we propose a different approach to acoustic anomaly detection. We use features extracted from NNs pretrained with image classification to train anomaly detection models, which is inspired by the success of these features in other areas, such as snore sound classification [16], emotion recognition in speech [17], music information retrieval [18] and medical applications [19].…”

Section: Related Workmentioning

confidence: 99%

Acoustic Anomaly Detection for Machine Sounds based on Image Transfer Learning

Müller¹,

Ritz²,

Illium³

et al. 2021

Proceedings of the 13th International Conference on Agents and Artificial Intelligence

View full text Add to dashboard Cite

In industrial applications, the early detection of malfunctioning factory machinery is crucial. In this paper, we consider acoustic malfunction detection via transfer learning. Contrary to the majority of current approaches which are based on deep autoencoders, we propose to extract features using neural networks that were pretrained on the task of image classification. We then use these features to train a variety of anomaly detection models and show that this improves results compared to convolutional autoencoders in recordings of four different factory machines in noisy environments. Moreover, we find that features extracted from ResNet based networks yield better results than those from AlexNet and Squeezenet. In our setting, Gaussian Mixture Models and One-Class Support Vector Machines achieve the best anomaly detection performance.

show abstract

Deep Unsupervised Representation Learning for Audio-Based Medical Applications

Cited by 5 publications

References 47 publications

The ACM Multimedia 2022 Computational Paralinguistics Challenge

The ACM Multimedia 2022 Computational Paralinguistics Challenge

Face mask recognition from audio: The MASC database and an overview on the mask challenge

Acoustic Anomaly Detection for Machine Sounds based on Image Transfer Learning

Contact Info

Product

Resources

About