Alzheimer's Dementia Recognition through Spontaneous Speech: The ADReSS Challenge

Luz, Saturnino; Haider, Fasih; Fuente, Sofía de la; Fromm, Davida; MacWhinney, Brian

doi:10.48550/arxiv.2004.06833

Cited by 23 publications

(43 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A. Datasets 1) Dementia: We use the standardized and benchmark ADReSS (Alzheimer's Dementia Recognition through Spontaneous Speech) dataset 1 [50]. This dataset consists of speech samples (WAV format) and transcripts (CHA format), and their corresponding 'MMSE' (Mini-Mental State Examination) scores as labels for regression.…”

Section: Experiments and Resultsmentioning

confidence: 99%

Uncertainty-Aware Boosted Ensembling in Multi-Modal Settings

Sarawgi¹,

Khincha²,

Zulfikar³

et al. 2021

Preprint

View full text Add to dashboard Cite

Reliability of machine learning (ML) systems is crucial in safety-critical applications such as healthcare, and uncertainty estimation is a widely researched method to highlight the confidence of ML systems in deployment. Sequential and parallel ensemble techniques have shown improved performance of ML systems in multi-modal settings by leveraging the feature sets together. We propose an uncertainty-aware boosting technique for multi-modal ensembling in order to focus on the data points with higher associated uncertainty estimates, rather than the ones with higher loss values. We evaluate this method on healthcare tasks related to Dementia and Parkinson's disease which involve real-world multi-modal speech and text data, wherein our method shows an improved performance. Additional analysis suggests that introducing uncertainty-awareness into the boosted ensembles decreases the overall entropy of the system, making it more robust to heteroscedasticity in the data, as well as better calibrating each of the modalities along with high quality prediction intervals. We open-source our entire codebase at https://github.com/usarawgi911/Uncertainty-aware-boosting.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Uncertainty-Aware Boosted Ensembling in Multi-Modal Settings

Sarawgi¹,

Khincha²,

Zulfikar³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Recorded participants were required to provide the descriptions of the Cookie Theft picture from the Boston Diagnostic Aphasia Examination [23]. Speech recordings were segmented using Voice Activity Detection (VAD) and later normalised [20]. The dataset contained both full enhanced audio, and normalised audio chunks.…”

Section: Corpusmentioning

confidence: 99%

“…Regardless of the approach used, the studies existing in the literature are difficult to analyze and compare due to the different datasets used. In this scenario, the Alzheimers Dementia Recognition through Spontaneous Speech (ADReSS) challenge has been proposed, with the aim of providing researchers with a common, statistically balanced and acoustically enhanced dataset to test their approaches [20].…”

Section: Introductionmentioning

confidence: 99%

The INESC-ID Multi-Modal System for the ADReSS 2020 Challenge

Pompili¹,

Rolland²,

Abad³

2020

Interspeech 2020

View full text Add to dashboard Cite

This paper describes a multi-modal approach for the automatic detection of Alzheimer's disease proposed in the context of the INESC-ID Human Language Technology Laboratory participation in the ADReSS 2020 challenge. Our classification framework takes advantage of both acoustic and textual feature embeddings, which are extracted independently and later combined. Speech signals are encoded into acoustic features using DNN speaker embeddings extracted from pre-trained models. For textual input, contextual embedding vectors are first extracted using an English Bert model and then used either to directly compute sentence embeddings or to feed a bidirectional LSTM-RNNs with attention. Finally, an SVM classifier with linear kernel is used for the individual evaluation of the three systems. Our best system, based on the combination of linguistic and acoustic information, attained a classification accuracy of 81.25%. Results have shown the importance of linguistic features in the classification of Alzheimer's Disease, which outperforms the acoustic ones in terms of accuracy. Early stage features fusion did not provide additional improvements, confirming that the discriminant ability conveyed by speech in this case is smooth out by linguistic data.

show abstract

“…A tremendous amount of effort has been made toward early detection of the disease [1]. Studies in [2][3][4][5][6][7] suggested the early symptoms of AD were detectable from spontaneous speech. Technologies that enable automatic analysis of human speech are considered a promising solution to this problem.…”

Section: Introductionmentioning

confidence: 99%