Explainability for Speech Models: On the Challenges of Acoustic Feature Selection

Dennis Fucci, Beatrice Savoldi, Marco Gaido, Matteo Negri, Mauro Cettolo, Luisa Bentivogli


Abstract
Spurred by the demand for transparency and interpretability in Artificial Intelligence (AI), the field of eXplainable AI (XAI) has experienced significant growth, marked by both theoretical reflections and technical advancements. While various XAI techniques, especially feature attribution methods, have been extensively explored across diverse tasks, their adaptation for the speech modality is lagging behind. We argue that a key factor hindering the diffusion of such methods in speech processing research lies in the complexity of defining interpretable acoustic features. In this paper, we discuss the key challenges in selecting the features for speech explanations. Also in light of existing research, we highlight current gaps and propose future avenues to enhance the depth and informativeness of explanations for speech.
Anthology ID:
2024.clicit-1.45
Volume:
Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)
Month:
December
Year:
2024
Address:
Pisa, Italy
Editors:
Felice Dell'Orletta, Alessandro Lenci, Simonetta Montemagni, Rachele Sprugnoli
Venue:
CLiC-it
SIG:
Publisher:
CEUR Workshop Proceedings
Note:
Pages:
373–381
Language:
URL:
https://aclanthology.org/2024.clicit-1.45/
DOI:
Bibkey:
Cite (ACL):
Dennis Fucci, Beatrice Savoldi, Marco Gaido, Matteo Negri, Mauro Cettolo, and Luisa Bentivogli. 2024. Explainability for Speech Models: On the Challenges of Acoustic Feature Selection. In Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024), pages 373–381, Pisa, Italy. CEUR Workshop Proceedings.
Cite (Informal):
Explainability for Speech Models: On the Challenges of Acoustic Feature Selection (Fucci et al., CLiC-it 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.clicit-1.45.pdf