Anna Pompili
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Anna Pompili has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Alberto Abad
INESC-ID research center, Instituto Superior Tcnico, Universidade de Lisboa, Lisboa, Portugal
7 shared publications - Isabel Pavão Martins
Centro de Estudos Egas Moniz, Faculty of Medicine, University of Lisbon, Lisbon, Portugal
4 shared publications - Isabel Trancoso
INESC-ID Lisbon
3 shared publications - David Martins de Matos
INESC-ID Lisboa R. Alves Redol 9 1000-029 Lisboa Portugal
2 shared publications Angela Costa
1 shared publication- Carlos David Martinez Hinarejos
Universitat Politècnica de València
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 6 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 19 (5) , 717-730
Unveiling Interpretability in Self-Supervised Speech Representations for Parkinson's Diagnosis
Recent works in pathological speech analysis have increasingly relied on powerful self-supervised speech representations, leading to promising results. However, the complex, black-box nature of these embeddings and the limited research on their interpretability significantly restrict their adoption for clinical diagnosis. To address this gap, we propose a novel, interpretable framework specifically designed to support Parkinson's Disease (PD) diagnosis. Through the design of simple yet effective cross-attention mechanisms for both embedding- and temporal-level analysis, the proposed framework offers interpretability from two distinct but complementary perspectives. Experimental findings across five well-established speech benchmarks for PD detection demonstrate the framework's capability to identify meaningful speech patterns within self-supervised representations for a wide range of assessment tasks. Fine-grained temporal analyses further underscore its potential to enhance the interpretability of deep-learning pathological speech models, paving the way for the development of more transparent, trustworthy, and clinically applicable computer-assisted diagnosis systems in this domain. Moreover, in terms of classification accuracy, our method achieves results competitive with state-of-the-art approaches, while also demonstrating robustness in cross-lingual scenarios when applied to spontaneous speech production.
- 6 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 19 (5) , 717-730
Top Cited PapersOpen AccessUnveiling Interpretability in Self-Supervised Speech Representations for Parkinson's Diagnosis
Recent works in pathological speech analysis have increasingly relied on powerful self-supervised speech representations, leading to promising results. However, the complex, black-box nature of these embeddings and the limited research on their interpretability significantly restrict their adoption for clinical diagnosis. To address this gap, we propose a novel, interpretable framework specifically designed to support Parkinson's Disease (PD) diagnosis. Through the design of simple yet effective cross-attention mechanisms for both embedding- and temporal-level analysis, the proposed framework offers interpretability from two distinct but complementary perspectives. Experimental findings across five well-established speech benchmarks for PD detection demonstrate the framework's capability to identify meaningful speech patterns within self-supervised representations for a wide range of assessment tasks. Fine-grained temporal analyses further underscore its potential to enhance the interpretability of deep-learning pathological speech models, paving the way for the development of more transparent, trustworthy, and clinically applicable computer-assisted diagnosis systems in this domain. Moreover, in terms of classification accuracy, our method achieves results competitive with state-of-the-art approaches, while also demonstrating robustness in cross-lingual scenarios when applied to spontaneous speech production.
- 24 February 2020
- Published by Springer Nature
- p. 43-52
Evaluation and Extensions of an Automatic Speech Therapy Platform
- 24 February 2020
- Published by Springer Nature
- p. 43-52
Evaluation and Extensions of an Automatic Speech Therapy Platform
- 20 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 14 (2) , 261-271
Pragmatic Aspects of Discourse Production for the Automatic Identification of Alzheimer's Disease
Clinical literature provides convincing evidence that language deficits in Alzheimer's disease (AD) allow for distinguishing patients with dementia from healthy subjects. Currently, computational approaches have widely investigated lexicosemantic aspects of discourse production, while pragmatic aspects like cohesion and coherence, are still mostly unexplored. In this article, we aim at providing a more comprehensive characterization of language abilities for the automatic identification of AD in narrative description tasks by also incorporating pragmatic aspects of speech production. To this end, we investigate the relevance of a recently proposed set of pragmatic features extracted from an automatically generated topic hierarchy graph in combination with a complementary set of state-of-the-art features encoding lexical, syntactic and semantic cues. Experimental results on the DementiaBank corpus show an accuracy improvement from 82.6% to 85.5% in identifying AD patients when pragmatic features are incorporated to the set of lexicosemantic features. Nevertheless, these results are obtained relying on manual transcriptions, which strongly limits the applicability of computational analysis to clinical settings. Thus, in this work we additionally carry out an analysis of the errors introduced by a speech recognition system and the way in which they impact the performance of the proposed method. In spite of the high word error rates obtained on these data (~40%), automatic AD identification accuracy decreased only to 79.7%, which is considered a remarkable result when compared with solutions based on manual transcriptions.
- 20 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 14 (2) , 261-271
Pragmatic Aspects of Discourse Production for the Automatic Identification of Alzheimer's Disease
Clinical literature provides convincing evidence that language deficits in Alzheimer's disease (AD) allow for distinguishing patients with dementia from healthy subjects. Currently, computational approaches have widely investigated lexicosemantic aspects of discourse production, while pragmatic aspects like cohesion and coherence, are still mostly unexplored. In this article, we aim at providing a more comprehensive characterization of language abilities for the automatic identification of AD in narrative description tasks by also incorporating pragmatic aspects of speech production. To this end, we investigate the relevance of a recently proposed set of pragmatic features extracted from an automatically generated topic hierarchy graph in combination with a complementary set of state-of-the-art features encoding lexical, syntactic and semantic cues. Experimental results on the DementiaBank corpus show an accuracy improvement from 82.6% to 85.5% in identifying AD patients when pragmatic features are incorporated to the set of lexicosemantic features. Nevertheless, these results are obtained relying on manual transcriptions, which strongly limits the applicability of computational analysis to clinical settings. Thus, in this work we additionally carry out an analysis of the errors introduced by a speech recognition system and the way in which they impact the performance of the proposed method. In spite of the high word error rates obtained on these data (~40%), automatic AD identification accuracy decreased only to 79.7%, which is considered a remarkable result when compared with solutions based on manual transcriptions.
- 21 November 2018
- Published by International Speech Communication Association
Topic coherence analysis for the classification of Alzheimer's disease
- 21 November 2018
- Published by International Speech Communication Association
Topic coherence analysis for the classification of Alzheimer's disease
- 29 July 2017
- Published by Springer Nature
- p. 411-419
Automatic Detection of Parkinson’s Disease: An Experimental Analysis of Common Speech Production Tasks Used for Diagnosis
- 29 July 2017
- Published by Springer Nature
- p. 411-419
Automatic Detection of Parkinson’s Disease: An Experimental Analysis of Common Speech Production Tasks Used for Diagnosis
- 1 September 2013
- Published by Elsevier in Computer Speech & Language
- Vol. 27 (6) , 1235-1248
Automatic word naming recognition for an on-line aphasia treatment system
- 1 September 2013
- Published by Elsevier in Computer Speech & Language
- Vol. 27 (6) , 1235-1248
Automatic word naming recognition for an on-line aphasia treatment system