Evaluating the COVID-19 Identification ResNet (CIdeR) on the INTERSPEECH COVID-19 from Audio Challenges

Akman, Alican; Coppock, Harry; Gaskell, Alexander; Tzirakis, Panagiotis; Jones, Lyn H.; Schuller, Björn W.

doi:10.48550/arxiv.2107.14549

Cited by 3 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Han et al, for example, showed that VGGish neural networks outperformed conventional methods in classifying different COVID-19 symptoms [35]. Akman et al developed a ResNet-like architecture for speech and coughbased COVID-19 detection [41]. The Bi-directional Long-Short-Term-Memory (BiLSTM) neural network was used in the top-performing system competing in the second Diagnosis of COVID-19 using Acoustics (DiCOVA2) Challenge [12].…”

Section: Related Work a Speech-based Covid-19 Diagnosticsmentioning

confidence: 99%

On the Impact of Voice Anonymization on Speech Diagnostic Applications: A Case Study on COVID-19 Detection

Zhu,

Imoussaïne-Aïkous,

Côté-Lussier

et al. 2024

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

With advances seen in deep learning, voice-based applications are burgeoning, ranging from personal assistants, affective computing, to remote disease diagnostics. As the voice contains both linguistic and para-linguistic information (e.g., vocal pitch, intonation, speech rate, loudness), there is growing interest in voice anonymization to preserve speaker privacy and identity. Voice privacy challenges have emerged over the last few years and focus has been placed on removing speaker identity while keeping linguistic content intact. For affective computing and disease monitoring applications, however, the para-linguistic content may be more critical. Unfortunately, the effects that anonymization may have on these systems are still largely unknown. In this paper, we fill this gap and focus on one particular health monitoring application: speech-based COVID-19 diagnosis. We test three anonymization methods and their impact on five different state-of-the-art COVID-19 diagnostic systems using three public datasets. We validate the effectiveness of the anonymization methods, compare their computational complexity, and quantify the impact across different testing scenarios for both within-and across-dataset conditions. Additionally, we provided a comprehensive evaluation of the importance of different speech aspects for diagnostics and showed how they are affected by different types of anonymizers. Lastly, we show the benefits of using anonymized external data as a data augmentation tool to help recover some of the COVID-19 diagnostic accuracy loss seen with anonymization.

show abstract

Section: Related Work a Speech-based Covid-19 Diagnosticsmentioning

confidence: 99%

On the Impact of Voice Anonymization on Speech Diagnostic Applications: A Case Study on COVID-19 Detection

Zhu,

Imoussaïne-Aïkous,

Côté-Lussier

et al. 2024

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

show abstract

“…This encompasses the traditional diagnostic system evaluation and serves as a baseline of the maximum accuracy that can be achieved by each model. As data distributions vary across datasets [68], diagnostics performance obtained under within-dataset conditions may lack external validity and has been shown to be over-optimistic [41], [44], [68]. To ensure the generalizability of the tested methods, for each scenario we explore both within-and crossdataset results.…”

Section: B Tasksmentioning

confidence: 99%

On the importance of different cough phases for COVID-19 detection

Zhu¹,

Shaik²,

Falk³

2022

Preprint

View full text Add to dashboard Cite

<p>Cough is an important symptom of numerous respiratory diseases, including COVID-19. While different cough phases (i.e., inhalation, compression, and expulsion) have been shown to be related to different pathological origins, existing cough-based COVID-19 detection systems rely on the entire cough recording, thus such phase-related characteristics are overlooked. In this study, our aim is two-fold. First, we have annotated over 1,250 cough recordings from two publicly-available cough sound databases, thus providing the research community with fine-grained cough phase labels. Next, we extract a number of temporal and acoustic features from each cough phase and test their usefulness and complementarity for COVID-19 detection. Experiments show the importance of cough phase segmentation, not only for improved COVID-19 detection, but also for the development of models that are interpretable and can better generalize across datasets.</p>

show abstract

“…The optimal hyperparameters used for the final CRNN model are summarized in Table III. In contrast to several existing systems (e.g., [8], [12]), no oversampling or data augmentation techniques were employed with the MTR-CRNN system. This was chosen as one of our goals is to better interpret the features being used by the model and data augmentation methods could bias our findings.…”

Section: Training and Inference Strategiesmentioning

confidence: 99%

“…A similar BiLSTM model was used in the winning system of the DiCOVA2 challenge [11]. Akman et al, in turn, proposed a 9-layer convolutional residual network and achieved an AUC-ROC of 78.7% on ComParE and 78.6% on DiCOVA [12].…”

Section: Introductionmentioning

confidence: 99%

“…While the spectrogram provides details about linguistic and paralinguistic content [14], it is known that it is sensitive to environmental artifacts (e.g., background noise and/or room reverberation) and may be sub-optimal for speech diagnostics. In fact, recent studies have shown that the performance of CNN based COVID-19 detection systems could degrade to chance-level when tested on unseen datasets [12], [15], [16]. As COVID-19 speech recordings are often collected "in-the-wild", care must be taken to ensure that environmental noise does not hamper diagnostic accuracy.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spectral-Temporal Saliency Masks and Modulation Tensorgrams for Generalizable COVID-19 Detection

Falk¹

2022

Preprint

View full text Add to dashboard Cite

<p>Speech COVID-19 detection systems have gained popularity as they represent an easy-to-use and low-cost solution that is well suited for at-home long-term monitoring of patients with persistent symptoms. Recently, however, the limited generalization capability of existing deep neural network based systems to unseen datasets has been raised as a serious concern, as has their limited interpretability. In this paper, we propose two innovations to help overcome these issues. First, we propose the use of a 3-dimensional modulation frequency tensor (called modulation tensorgram representation, MTR) as input to a convolutional recurrent neural network for COVID-19 detection. The representation is known to provide robustness against different environmental factors seen across datasets. Next, we propose the use of spectro-temporal saliency masking to aggregate regions of the MTR related to COVID-19, thus helping further improve the generalizability and interpretability of the model. Experiments are conducted on three public datasets and results show the proposed solution consistently outperforming two benchmark systems in within-, across-, and unseen-dataset tests. The proposed method relies on a similar number of parameters to the benchmark, thus a promising solution for at-home monitoring of COVID-19 infection. </p>

show abstract

Evaluating the COVID-19 Identification ResNet (CIdeR) on the INTERSPEECH COVID-19 from Audio Challenges

Cited by 3 publications

References 15 publications

On the Impact of Voice Anonymization on Speech Diagnostic Applications: A Case Study on COVID-19 Detection

On the Impact of Voice Anonymization on Speech Diagnostic Applications: A Case Study on COVID-19 Detection

On the importance of different cough phases for COVID-19 detection

Spectral-Temporal Saliency Masks and Modulation Tensorgrams for Generalizable COVID-19 Detection

Contact Info

Product

Resources

About