Automatic tools to detect hypernasality have been traditionally designed to analyze
sustained vowels exclusively. This is in sharp contrast with clinical recommendations, which consider
it 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 speech
samples 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, sustained
consonants, sustained vowel, words and sentences. The recordings were obtained, with the help
of a mobile app, from Spain, Chile and Ecuador. Multiple acoustic features were computed from
each utterance (e.g., MFCC, formant frequency) After a selection process, the best 20 features served
to train different classification algorithms. Accuracy was the highest with syllable sequences and
also with some words and sentences. Accuracy increased slightly by training the classifiers with
between two and three utterances. However, the best results were obtained by combining the results
of multiple classifiers. We conclude that protocols for automatic evaluation of hypernasality should
include a variety of utterance types. It seems feasible to detect hypernasality automatically with
mobile devices.
