The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation &amp;amp; Primates

Schuller, Björn W.; Batliner, Anton; Bergler, Christian; Mascolo, Cecilia; Han, Jing; Lefter, Iulia; Kaya, Heysem; Amiriparian, Shahin; Baird, Alice; Stappen, Lukas; Ottl, Sandra; Gerczuk, Maurice; Tzirakis, Panagiotis; Brown, Chloë; Chauhan, Jagmohan; Grammenos, Andreas; Hasthanasombat, Apinan; Spathis, Dimitris; Tong, Xia; Cicuta, Pietro; Rothkrantz, Léon J. M.; Zwerts, Joeri A.; Treep, Jelle; Kaandorp, Casper S.

doi:10.21437/interspeech.2021-19

Cited by 87 publications

(105 citation statements)

References 10 publications

Supporting

Mentioning

101

Contrasting

Unclassified

Order By: Relevance

“…In the INTERPSEECH 2021 ComParE ( 19 ), the CCS provides a dataset from the crowd-sourced Cambridge COVID-19 Sound database ( 15 ). The participants are asked to provide one to three forced coughs in each recording via one of the following multiple platforms: A web interface, an Android app, and an iOS app.…”

Section: Resultsmentioning

confidence: 99%

“…With the chosen pre-trained COUGHVID models and their strategies (layer(s)/block(s) number and transfer learning strategies), we transfer the parameters or embeddings of the above chosen COUGHVID models to the current train-from-scratch models on the ComParE and DiCOVA datasets during the training. Finally, we choose the best results to compete with official baselines: the average validation AUC 68.81% ( 20 ) for the DiCOVA Track-1 dataset, and test UAR without fusion 64.7% ( 19 ) for ComParE CCS. Similarly, when training models from scratch or applying the incorporating embeddings method, we set the initial learning rate as 0.001, whereas if the transferring parameters are utilised, the initial learning rate is set as 0.0001.…”

Section: Resultsmentioning

confidence: 99%

“…The main purpose of this study is to introduce and prove the usefulness of the transfer learning framework CovNet, instead of competing with the state-of-the-art performance on the DiCOVA Track-1 dataset ( 54 – 56 ) and ComParE CCS dataset ( 19 ). The constructed four CNN models are so simple that each of them only contains three convolutional layers/blocks; we do not apply any data augmentation techniques and the only input to the networks are the original log Mel spectrograms.…”

Section: Resultsmentioning

confidence: 99%

“…Due to the gap in sound type between FluSense and databases with cough sounds only, the COUGHVID database is considered as the target data when CNNs are trained on FluSense as the source data. The trained models on COUGHVID are further adapted to the other two smaller test databases, i.e., Computational Paralinguistics challengE (ComParE) 2021 COVID-19 cough sub-challenge (CCS) ( 19 ) and DiCOVA 2021 Track-1 ( 20 ).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

CovNet: A Transfer Learning Framework for Automatic COVID-19 Detection From Crowd-Sourced Cough Sounds

Chang

Jing

Ren

et al. 2022

Front. Digit. Health

Self Cite

View full text Add to dashboard Cite

Since the COronaVIrus Disease 2019 (COVID-19) outbreak, developing a digital diagnostic tool to detect COVID-19 from respiratory sounds with computer audition has become an essential topic due to its advantages of being swift, low-cost, and eco-friendly. However, prior studies mainly focused on small-scale COVID-19 datasets. To build a robust model, the large-scale multi-sound FluSense dataset is utilised to help detect COVID-19 from cough sounds in this study. Due to the gap between FluSense and the COVID-19-related datasets consisting of cough only, the transfer learning framework (namely CovNet) is proposed and applied rather than simply augmenting the training data with FluSense. The CovNet contains (i) a parameter transferring strategy and (ii) an embedding incorporation strategy. Specifically, to validate the CovNet's effectiveness, it is used to transfer knowledge from FluSense to COUGHVID, a large-scale cough sound database of COVID-19 negative and COVID-19 positive individuals. The trained model on FluSense and COUGHVID is further applied under the CovNet to another two small-scale cough datasets for COVID-19 detection, the COVID-19 cough sub-challenge (CCS) database in the INTERSPEECH Computational Paralinguistics challengE (ComParE) challenge and the DiCOVA Track-1 database. By training four simple convolutional neural networks (CNNs) in the transfer learning framework, our approach achieves an absolute improvement of 3.57% over the baseline of DiCOVA Track-1 validation of the area under the receiver operating characteristic curve (ROC AUC) and an absolute improvement of 1.73% over the baseline of ComParE CCS test unweighted average recall (UAR).

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

CovNet: A Transfer Learning Framework for Automatic COVID-19 Detection From Crowd-Sourced Cough Sounds

Chang

Jing

Ren

et al. 2022

Front. Digit. Health

Self Cite

View full text Add to dashboard Cite

show abstract

“…The research applied within this contribution is a continuation of experiments, which were included as part of the "Escalation" sub-challenge for the INTERSPEECH 2021 COMPARE Challenge (Schuller et al, 2021). For the experiments that were part of the challenge, two out of the three datasets utilized in this study were applied in a similar cross-corpus manner, where one was used for training and the other for testing.…”

Section: Related Workmentioning

confidence: 99%

A Cross-Corpus Speech-Based Analysis of Escalating Negative Interactions

Lefter

Baird

Stappen

et al. 2022

Front. Comput. Sci.

Self Cite

View full text Add to dashboard Cite

The monitoring of an escalating negative interaction has several benefits, particularly in security, (mental) health, and group management. The speech signal is particularly suited to this, as aspects of escalation, including emotional arousal, are proven to easily be captured by the audio signal. A challenge of applying trained systems in real-life applications is their strong dependence on the training material and limited generalization abilities. For this reason, in this contribution, we perform an extensive analysis of three corpora in the Dutch language. All three corpora are high in escalation behavior content and are annotated on alternative dimensions related to escalation. A process of label mapping resulted in two possible ground truth estimations for the three datasets as low, medium, and high escalation levels. To observe class behavior and inter-corpus differences more closely, we perform acoustic analysis of the audio samples, finding that derived labels perform similarly across each corpus, with escalation interaction increasing in pitch (F0) and intensity (dB). We explore the suitability of different speech features, data augmentation, merging corpora for training, and testing on actor and non-actor speech through our experiments. We find that the extent to which merging corpora is successful depends greatly on the similarities between label definitions before label mapping. Finally, we see that the escalation recognition task can be performed in a cross-corpus setup with hand-crafted speech features, obtaining up to 63.8% unweighted average recall (UAR) at best for a cross-corpus analysis, an increase from the inter-corpus results of 59.4% UAR.

show abstract

Neuromorphic Computing via Fission‐based Broadband Frequency Generation

Fischer,

Chemnitz,

Zhu

et al. 2023

Advanced Science

View full text Add to dashboard Cite

The performance limitations of traditional computer architectures have led to the rise of brain‐inspired hardware, with optical solutions gaining popularity due to the energy efficiency, high speed, and scalability of linear operations. However, the use of optics to emulate the synaptic activity of neurons has remained a challenge since the integration of nonlinear nodes is power‐hungry and, thus, hard to scale. Neuromorphic wave computing offers a new paradigm for energy‐efficient information processing, building upon transient and passively nonlinear interactions between optical modes in a waveguide. Here, an implementation of this concept is presented using broadband frequency conversion by coherent higher‐order soliton fission in a single‐mode fiber. It is shown that phase encoding on femtosecond pulses at the input, alongside frequency selection and weighting at the system output, makes transient spectro‐temporal system states interpretable and allows for the energy‐efficient emulation of various digital neural networks. The experiments in a compact, fully fiber‐integrated setup substantiate an anticipated enhancement in computational performance with increasing system nonlinearity. The findings suggest that broadband frequency generation, accessible on‐chip and in‐fiber with off‐the‐shelf components, may challenge the traditional approach to node‐based brain‐inspired hardware design, ultimately leading to energy‐efficient, scalable, and dependable computing with minimal optical hardware requirements.

show abstract

The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & Primates

Cited by 87 publications

References 10 publications

CovNet: A Transfer Learning Framework for Automatic COVID-19 Detection From Crowd-Sourced Cough Sounds

CovNet: A Transfer Learning Framework for Automatic COVID-19 Detection From Crowd-Sourced Cough Sounds

A Cross-Corpus Speech-Based Analysis of Escalating Negative Interactions

Neuromorphic Computing via Fission‐based Broadband Frequency Generation

Contact Info

Product

Resources

About