Automatic Assessment of Speech Intelligibility using Consonant Similarity for Head and Neck Cancer - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Automatic Assessment of Speech Intelligibility using Consonant Similarity for Head and Neck Cancer

Résumé

The automatic prediction of speech intelligibility is a widely known problem in the context of pathological speech. It has been seen as a growing and viable alternative to perceptual evaluation, which is typically time-consuming, highly subjective and strongly biased. Due to this, the development of automatic systems that are able to output not only unbiased predictions, but also interpretable scores become relevant. In this paper we investigate a method to predict speech intelligibility based on consonant phonetic similarity. The proposed methodology relies on a siamese network to compute similarity scores between healthy and pathological phonemes, and based on the combination of those scores, regresses the intelligibility values. Our experimental evaluation suggests a high baseline correlation value of p = 0.82, when applied to our corpus of head and neck cancer. Moreover, further conditioning of the system on specific phonemes in key contexts increased the correlation up to p = 0.89. The given methodology also aims to promote interpretability of the predicted intelligibility score, which is highly relevant in a clinical setting.
Fichier principal
Vignette du fichier
Interspeech_2022__Siamese_Networks.pdf (353.11 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03716420 , version 1 (07-07-2022)

Identifiants

  • HAL Id : hal-03716420 , version 1

Citer

Sebastião Quintas, Julie Mauclair, Virginie Woisard, Julien Pinquier. Automatic Assessment of Speech Intelligibility using Consonant Similarity for Head and Neck Cancer. 23rd INTERSPEECH Conference: Human and Humanizing Speech Technology ( INTERSPEECH 2022), Sep 2022, Incheon, South Korea. à paraître. ⟨hal-03716420⟩
168 Consultations
143 Téléchargements

Partager

Gmail Facebook X LinkedIn More