RT Journal Article
T1 Unmasking Nasality to Assess Hypernasality
A1 Moreno-Torres-Sánchez, Ignacio
A1 Lozano, Andres
A1 Bermúdez-de-Alvear, Rosa María
A1 Pino, Josue
A1 Garcia-Mendez, María Dolores
A1 Nava-Baro, Enrique
K1 Hipernasalidad
AB Automatic evaluation of hypernasality has been traditionally computed using monophonicsignals (i.e., combining nose and mouth signals). Here, this study aimed to examine if nose signalsserve to increase the accuracy of hypernasality evaluation. Using a conventional microphone and aNasometer, we recorded monophonic, mouth, and nose signals. Three main analyses were performed:(1) comparing the spectral distance between oral/nasalized vowels in monophonic, nose, and mouthsignals; (2) assessing the accuracy of Deep Neural Network (DNN) models in classifying oral/nasalsounds and vowel/consonant sounds trained with nose, mouth, and monophonic signals; (3) analyzingthe correlation between DNN-derived nasality scores and expert-rated hypernasality scores. Thedistance between oral and nasalized vowels was the highest in the nose signals. Moreover, DNNmodels trained on nose signals outperformed in nasal/oral classification (accuracy: 0.90), but wereslightly less precise in vowel/consonant differentiation (accuracy: 0.86) compared to models trainedon other signals. A strong Pearson’s correlation (0.83) was observed between nasality scores fromDNNs trained with nose signals and human expert ratings, whereas those trained on mouth signalsshowed a weaker correlation (0.36). We conclude that mouth signals partially mask the nasalityinformation carried by nose signals. Significance: the accuracy of hypernasality assessment tools mayimprove by analyzing nose signals.
PB MDPI
YR 2023
FD 2023-11-23
LK https://hdl.handle.net/10630/33114
UL https://hdl.handle.net/10630/33114
LA eng
NO Moreno-Torres, I.; Lozano, A.; Bermúdez, R.; Pino, J.; Méndez, M.D.G.; Nava, E. Unmasking Nasality to Assess Hypernasality. Appl. Sci. 2023, 13, 12606. https:// doi.org/10.3390/app132312606
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 20 ene 2026