The Ustc System for Adress-m Challenge

Mei, Kangdi; Ding, Xinyun; Liu, Yinlong; Guo, Zhiqiang; Xu, Feiyang; Li, Xin; Naren, Tuya; Yuan, Jiahong; Ling, Zhen-Hua

doi:10.1109/icassp49357.2023.10094714

Cited by 7 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering the small size of the ADReSS-M data set and the fact that the picture descriptions were different in the training and test sets (not only in language but also in content, as the pictures were different), we expected that the proposed models would rely on more abstract acoustic features rather than on lexical or structural linguistic features, as the former are presumably less language-dependent than the latter [ 26 ], [ 59 ], [ 60 ]. Indeed this was the case for most submissions, as four of the top-scoring teams [ 46 ], [ 49 ], [ 50 ], [ 51 ] employed acoustic features exclusively (even though in some cases ASR output was employed to derive dysfluency and pause features). However, some of the submitted models, including one of the top-5 [ 52 ] employed linguistic features, either by themselves or in combination with acoustic and paralinguistic features.…”

Section: Discussionmentioning

confidence: 99%

“…The team that came in second place employed a mixed-batch transfer learning approach for both tasks, applied to eGeMAPS acoustic features [ 49 ]. The third highest scoring team explored a wider number of acoustic feature extraction methods, employing an XGBoost classifier for the classification task and SVM and XGBoost regressors for MMSE prediction [ 50 ]. The fourth ranked team employed an automatic speech recognition system to derive speech intelligibility features based on confidence scores assigned by the system, which along with word-level duration and pause features formed the input for logistic regression and SVM regression models for tasks 1 and 2, respectively [ 51 ].…”

Section: Rank Of Submissionsmentioning

confidence: 99%

“…Mei et al [ 50 ] provide insights into the methodologies, techniques, and algorithms employed by the USTC team to tackle the ADReSS-M Challenge. They discuss their system’s architecture, data preprocessing, feature extraction methods, and machine learning or deep learning models used for emotion recognition in speech.…”

Section: Descriptions Of the Top-5 Submissionsmentioning

confidence: 99%

See 2 more Smart Citations

An Overview of the ADReSS-M Signal Processing Grand Challenge on Multilingual Alzheimer's Dementia Recognition Through Spontaneous Speech

Luz,

Haider,

Fromm

et al. 2024

IEEE Open J. Signal Process.

View full text Add to dashboard Cite

The challenge targeted difficult automatic prediction problems of great societal and medical relevance, namely, the detection of Alzheimer's Dementia (AD) and the estimation of cognitive test scoress. Participants were invited to create models for assessment of cognitive function based on spontaneous speech data. Most of these models employed signal processing and machine learning methods. The ADReSS-M challenge was designed to assess the extent to which predictive models built based on speech in one language generalise to another language. The language data compiled and made available for ADReSS-M comprised English, for model training, and Greek, for model testing and validation. To the best of our knowledge no previous shared research task investigated acoustic features of the speech signal or linguistic characteristics in the context of multilingual AD detection. This paper describes the context of the ADReSS-M challenge, its data sets, its predictive tasks, the evaluation methodology we employed, our baseline models and results, and the top five submissions. The paper concludes with a summary discussion of the ADReSS-M results, and our critical assessment of the future outlook in this field.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Rank Of Submissionsmentioning

confidence: 99%

Section: Descriptions Of the Top-5 Submissionsmentioning

confidence: 99%

See 1 more Smart Citation

An Overview of the ADReSS-M Signal Processing Grand Challenge on Multilingual Alzheimer's Dementia Recognition Through Spontaneous Speech

Luz,

Haider,

Fromm

et al. 2024

IEEE Open J. Signal Process.

View full text Add to dashboard Cite

show abstract

Identifying Alzheimer’s Disease Across Cognitive Impairment Spectrum Using Acoustic Features Only

Jon,

Jung,

Jin

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Speech based detection of Alzheimer’s disease: a survey of AI techniques, datasets and challenges

Ding,

Chetty,

Noori Hoshyar

et al. 2024

Artif Intell Rev

View full text Add to dashboard Cite

Alzheimer’s disease (AD) is a growing global concern, exacerbated by an aging population and the high costs associated with traditional detection methods. Recent research has identified speech data as valuable clinical information for AD detection, given its association with the progressive degeneration of brain cells and subsequent impacts on memory, cognition, and language abilities. The ongoing demographic shift toward an aging global population underscores the critical need for affordable and easily available methods for early AD detection and intervention. To address this major challenge, substantial research has recently focused on investigating speech data, aiming to develop efficient and affordable diagnostic tools that align with the demands of our aging society. This paper presents an in-depth review of studies from 2018–2023 utilizing speech for AD detection. Following the PRISMA protocol and a two-stage selection process, we identified 85 publications for analysis. In contrast to previous literature reviews, this paper places a strong emphasis on conducting a rigorous comparative analysis of various Artificial Intelligence (AI) based techniques, categorizing them meticulously based on underlying algorithms. We perform an exhaustive evaluation of research papers leveraging common benchmark datasets, specifically ADReSS and ADReSSo, to assess their performance. In contrast to previous literature reviews, this work makes a significant contribution by overcoming the limitations posed by the absence of standardized tasks and commonly accepted benchmark datasets for comparing different studies. The analysis reveals the dominance of deep learning models, particularly those leveraging pre-trained models like BERT, in AD detection. The integration of acoustic and linguistic features often achieves accuracies above 85%. Despite these advancements, challenges persist in data scarcity, standardization, privacy, and model interpretability. Future directions include improving multilingual recognition, exploring emerging multimodal approaches, and enhancing ASR systems for AD patients. By identifying these key challenges and suggesting future research directions, our review serves as a valuable resource for advancing AD detection techniques and their practical implementation.

show abstract

The Ustc System for Adress-m Challenge

Cited by 7 publications

References 4 publications

An Overview of the ADReSS-M Signal Processing Grand Challenge on Multilingual Alzheimer's Dementia Recognition Through Spontaneous Speech

An Overview of the ADReSS-M Signal Processing Grand Challenge on Multilingual Alzheimer's Dementia Recognition Through Spontaneous Speech

Identifying Alzheimer’s Disease Across Cognitive Impairment Spectrum Using Acoustic Features Only

Speech based detection of Alzheimer’s disease: a survey of AI techniques, datasets and challenges

Contact Info

Product

Resources

About