RT Journal Article
T1 Which Utterance Types Are Most Suitable to Detect Hypernasality Automatically?
A1 Moreno-Torres-Sánchez, Ignacio
A1 Lozano, Andrés
A1 Nava-Baro, Enrique
A1 Bermúdez-de-Alvear, Rosa María
K1 Hipernasalidad
AB Automatic tools to detect hypernasality have been traditionally designed to analyzesustained vowels exclusively. This is in sharp contrast with clinical recommendations, which considerit necessary to use a variety of utterance types (e.g., repeated syllables, sustained sounds, sentences,etc.) This study explores the feasibility of detecting hypernasality automatically based on speechsamples other than sustained vowels. The participants were 39 patients and 39 healthy controls.Six types of utterances were used: counting 1-to-10 and repetition of syllable sequences, sustainedconsonants, sustained vowel, words and sentences. The recordings were obtained, with the helpof a mobile app, from Spain, Chile and Ecuador. Multiple acoustic features were computed fromeach utterance (e.g., MFCC, formant frequency) After a selection process, the best 20 features servedto train different classification algorithms. Accuracy was the highest with syllable sequences andalso with some words and sentences. Accuracy increased slightly by training the classifiers withbetween two and three utterances. However, the best results were obtained by combining the resultsof multiple classifiers. We conclude that protocols for automatic evaluation of hypernasality shouldinclude a variety of utterance types. It seems feasible to detect hypernasality automatically withmobile devices.
PB MDPI
YR 2021
FD 2021-09-11
LK https://hdl.handle.net/10630/33113
UL https://hdl.handle.net/10630/33113
LA eng
NO Moreno-Torres, I.; Lozano, A.; Nava, E.; Bermúdez-de-Alvear, R. Which Utterance Types Are Most Suitable to Detect Hypernasality Automatically? Appl. Sci. 2021, 11, 8809. https://doi.org/10.3390/ app11198809
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 20 ene 2026