Interpreting Deep Representations of Phonetic Features via Neuro-based Concept Detector: Application to speech disorders due to Head and Neck cancer - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE/ACM Transactions on Audio, Speech and Language Processing Année : 2022

Interpreting Deep Representations of Phonetic Features via Neuro-based Concept Detector: Application to speech disorders due to Head and Neck cancer

Résumé

The popularity of Deep Neural Networks (DNNs) is growing significantly, and so is the interest in gaining a better understanding of their functioning. In this work, it is even more interesting to reveal the behavior of these blackboxes since we are involved in a clinical context. To this end, we propose a general analytic framework, named Neuro-based Concept Detector (NCD), for interpreting deep representations of a DNN. Based on the activation patterns of the hidden neurons, this framework highlights the capacity of neurons to detect a specific concept related to the final task. The key strength of our framework is that it provides an interpretability tool for any type of DNN performing a classification task regardless of the application field. In this paper, we evaluate this framework on a Convolutional Neural Network (CNN) trained for the task of French phone classification. This choice was guided by the final objective of a long-term research project, which aims to identify the linguistic units best contributing to the maintenance or loss of intelligibility in the context of speech disorders. Through NCD, we demonstrate the emergence of phonetic features in the classification layers of the CNN-based model, while applied on healthy speech, a concept with a great interest in the field of clinical phonetics. Indeed, we further show that these interesting findings shed light on the characteristics of speech disorders in terms of altered phonetic features and provide relevant information for clinical practice, notably, patients' rehabilitation and follow-up.
Fichier non déposé

Dates et versions

hal-03837530 , version 1 (02-11-2022)

Identifiants

Citer

Sondes Abderrazek, Corinne Fredouille, Alain Ghio, Muriel Lalain, Christine Meunier, et al.. Interpreting Deep Representations of Phonetic Features via Neuro-based Concept Detector: Application to speech disorders due to Head and Neck cancer. IEEE/ACM Transactions on Audio, Speech and Language Processing, 2022, pp.1-14. ⟨10.1109/TASLP.2022.3221039⟩. ⟨hal-03837530⟩
72 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More