Recognition of Echolalic Autistic Child Vocalisations Utilising Convolutional Recurrent Neural Networks

Amiriparian, Shahin; Baird, Alice; Julka, Sahib; Alcorn, Alyssa M.; Ottl, Sandra; Petrovic, Suncica; Ainger, Eloise; Cummins, Nicholas; Schuller, Björn

doi:10.21437/interspeech.2018-1772

Cited by 15 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The recent advancements in Deep Learning (DL) suggest that end-to-end learning (i.e., ML models that learn directly from the raw data and no features are needed) can outperform the classic, feature-based ML. For example, DL has achieved breakthrough performance in tasks such as pattern recognition problems [4], image processing [5], [6], natural language processing [7], [8], speech and audio processing [9], [10], and sensor data processing [11], [12]. For CHF detection, a successful combination of classic ML and end-to-end DL can outperform each single approach [13].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning and End-to-End Deep Learning for the Detection of Chronic Heart Failure From Heart Sounds

et al. 2020

View full text Add to dashboard Cite

Chronic heart failure (CHF) affects over 26 million of people worldwide, and its incidence is increasing by 2% annually. Despite the significant burden that CHF poses and despite the ubiquity of sensors in our lives, methods for automatically detecting CHF are surprisingly scarce, even in the research community. We present a method for CHF detection based on heart sounds. The method combines classic Machine-Learning (ML) and end-to-end Deep Learning (DL). The classic ML learns from expert features, and the DL learns from a spectro-temporal representation of the signal. The method was evaluated on recordings from 947 subjects from six publicly available datasets and one CHF dataset that was collected for this study. Using the same evaluation method as a recent PhysoNet challenge, the proposed method achieved a score of 89.3, which is 9.1 higher than the challenge's baseline method. The method's aggregated accuracy is 92.9% (error of 7.1%); while the experimental results are not directly comparable, this error rate is relatively close to the percentage of recordings labeled as ''unknown'' by experts (9.7%). Finally, we identified 15 expert features that are useful for building ML models to differentiate between CHF phases (i.e., in the decompensated phase during hospitalization and in the recompensated phase) with an accuracy of 93.2%. The proposed method shows promising results both for the distinction of recordings between healthy subjects and patients and for the detection of different CHF phases. This may lead to the easier identification of new CHF patients and the development of home-based CHF monitors for avoiding hospitalizations. INDEX TERMS Chronic heart failure, deep learning, heart sounds, machine learning, PCG.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine Learning and End-to-End Deep Learning for the Detection of Chronic Heart Failure From Heart Sounds

et al. 2020

View full text Add to dashboard Cite

show abstract

“…CapsNets were originally introduced to compensate the generalisation problem of CNNs towards observing novel viewpoints in images [16], [24]. CNNs using spectrograms as input often encounter difficulties when recognising data from classes with fine-grained similarities [31], [45], [46]. With this in mind, we developed our framework around CapsNets to evaluate whether a better generalisation for spectrogram classification can be achieved.…”

Section: Discussionmentioning

confidence: 99%

Audio-based Recognition of Bipolar Disorder Utilising Capsule Networks

Amiriparian

Awad

Gerczuk

et al. 2019

2019 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

Bipolar disorder (BD) is an acute mood condition, in which states can drastically shift from one extreme to another, considerably impacting an individual's wellbeing. Automatic recognition of a BD diagnosis can help patients to obtain medical treatment at an earlier stage and therefore have a better overall prognosis. With this in mind, in this study, we utilise a Capsule Neural Network (CapsNet) for audio-based classification of patients who were suffering from BD after a mania episode into three classes of Remission, Hypomania, and Mania. The CapsNet attempts to address the limitations of Convolutional Neural Networks (CNNs) by considering vital spatial hierarchies between the extracted images from audio files. We develop a framework around the CapsNet in order to analyse and classify audio signals. First, we create a spectrogram from short segments of speech recordings from individuals with a bipolar diagnosis. We then train the CapsNet on the spectrograms with 32 lowlevel and three high-level capsules, each for one of the BD classes. These capsules attempt both to form a meaningful representation of the input data and to learn the correct BD class. The output of each capsule represents an activity vector. The length of this vector encodes the presence of the corresponding type of BD in the input, and its orientation represents the properties of this specific instance of BD. We show that using our CapsNet framework, it is possible to achieve competitive results for the aforementioned task by reaching a UAR of 46.2 % and 45.5 % on the development and test partitions, respectively. Furthermore, the efficacy of our approach is compared with a sequence to sequence autoencoder and a CNN-based neural network.

show abstract

“…spektrogramy, cepstrogramy, chromagramy itp.) [6,30,31] lub postać parametryczną sygnału muzycznego, czyli wektor cech (np. wektor współczynników mel-cepstralnych lub parametry wykorzystujące standard MPEG-7) [13,14,16].…”

Section: Klasyfikacja Emocjiunclassified

Klasyfikacja emocji w muzyce filmowej z wykorzystaniem uczenia g��bokiego

Ciborowski¹,

Reginis²,

Weber³

et al. 2022

Post�py W In�ynierii D�wi�ku I Psychoakustyce

View full text Add to dashboard Cite

Praca przedstawia zagadnienia związane z klasyfikacją emocji w muzyce filmowej. W artykule zaproponowano model emocji zawierający dziewięć stanów emocjonalnych, do których przypisany jest kolor zgodnie z teorią koloru w filmie. Kolejne kroki eksperymentu obejmowały wybór muzyki filmowej do testów (baza Epidemic Sound), przygotowanie założeń ankiety oraz modelu emocji wykorzystywanych w testach odsłuchowych, a także konstrukcję ankiety. Ankieta została zrealizowana za pomocą formularzy Google. Przeprowadzono również analizę statystyczną wyników uzyskanych w testach subiektywnych. Częścią pracy jest opracowanie aplikacji do automatycznej klasyfikacji emocji na podstawie muzyki filmowej. Aplikacja wykorzystuje splotową sieć neuronową, która klasyfikuje emocje na bazie 30-sekundowych fragmentów muzyki reprezentowanych przez spektrogramy w skali melowej. W końcowej części pracy pokazano przykład wyników klasyfikacji emocji w muzyce filmowej uzyskanych za pomocą sieci neuronowej, zweryfikowanych w sposób subiektywny.

show abstract

Recognition of Echolalic Autistic Child Vocalisations Utilising Convolutional Recurrent Neural Networks

Cited by 15 publications

References 22 publications

Machine Learning and End-to-End Deep Learning for the Detection of Chronic Heart Failure From Heart Sounds

Machine Learning and End-to-End Deep Learning for the Detection of Chronic Heart Failure From Heart Sounds

Audio-based Recognition of Bipolar Disorder Utilising Capsule Networks

Klasyfikacja emocji w muzyce filmowej z wykorzystaniem uczenia g��bokiego

Contact Info

Product

Resources

About