OBJECTIVE MEASURES OF PLOSIVE NASALIZATION IN HYPERNASAL SPEECH

Consonant-Vowel Transition Models Based on Deep Learning for Objective Evaluation of Articulation

Spectro-temporal dynamics of consonant-vowel (CV) transition regions are considered to provide robust cues related to articulation. In this work, we propose an objective measure of precise articulation, dubbed the objective articulation measure (OAM), by analyzing the CV transitions segmented around vowel onsets. The OAM is derived based on the posteriors of a convolutional neural network pre-trained to classify between different consonants using CV regions as input. We demonstrate that the OAM is correlated with perceptual measures in a variety of contexts including (a) adult dysarthric speech, (b) the speech of children with cleft lip/palate, and (c) a database of accented English speech from native Mandarin and Spanish speakers.

A Deep Learning Algorithm for Objective Assessment of Hypernasality in Children With Cleft Palate

OBJECTIVES

Evaluation of hypernasality requires extensive perceptual training by clinicians and extending this training on a large scale internationally is untenable; this compounds the health disparities that already exist among children with cleft. In this work, we present the objective hypernasality measure (OHM), a speech-based algorithm that automatically measures hypernasality in speech, and validate it relative to a group of trained clinicians.

METHODS

We trained a deep neural network (DNN) on approximately 100 hours of a publicly-available healthy speech corpus to detect the presence of nasal acoustic cues generated through the production of nasal consonants and nasalized phonemes in speech. Importantly, this model does not require any clinical data for training. The posterior probabilities of the deep learning model were aggregated at the sentence and speaker-levels to compute the OHM.

RESULTS

The results showed that the OHM was significantly correlated with perceptual hypernasality ratings from the Americleft database (r = 0.797, p < 0.001) and the New Mexico Cleft Palate Center (NMCPC) database (r = 0.713, p < 0.001). In addition, we evaluated the relationship between the OHM and articulation errors; the sensitivity of the OHM in detecting the presence of very mild hypernasality; and established the internal reliability of the metric. Further, the performance of the OHM was compared with a DNN regression algorithm directly trained on the hypernasal speech samples.

SIGNIFICANCE

The results indicate that the OHM is able to measure the severity of hypernasality on par with Americleft-trained clinicians on thisdataset.

Reliability of Perceptual Judgments of Phonetic Accuracy and Hypernasality Among Speech-Language Pathologists for Children With Dysarthria

Purpose The objectives of this study were to: (a) compare interrater reliability of practicing speech-language pathologists' (SLPs) perceptual judgments of phonetic accuracy and hypernasality between children with dysarthria and those with typical development, and (b) to identify speech factors that influence reliability of these perceptual judgments for children with dysarthria. Method Ten SLPs provided ratings of speech samples from twenty 5-year-old children with dysarthria and twenty 5-year-old children with typical development on two tasks via a web-based platform: a hypernasality judgment task and a phonetic accuracy judgment task. Interrater reliability of SLPs' ratings on both tasks was compared between children with dysarthria and children with typical development. For children with dysarthria, four acoustic speech measures, intelligibility, and a measure of phonetic accuracy (percent stops correct) were examined as predictors of reliability of SLPs' perceptual judgments. Results Reliability of SLPs' phonetic accuracy judgments and hypernasality ratings was significantly lower for children with dysarthria than for children with typical development. Among children with dysarthria, interrater reliability of perceptual judgments ranged from strong to weak. Percent stops correct was the strongest predictor of interrater reliability for both phonetic accuracy judgments and hypernasality ratings. Conclusions Reliability of perceptual phonetic accuracy judgments and hypernasality ratings among practicing SLPs for children with dysarthria is reduced compared to ratings for children with typical development. Findings underscore the need for more reliable methods to assess phonetic accuracy and hypernasality for children with dysarthria.

Robust Estimation of Hypernasality in Dysarthria with Acoustic Model Likelihood Features

Hypernasality is a common characteristic symptom across many motor-speech disorders. For voiced sounds, hypernasality introduces an additional resonance in the lower frequencies and, for unvoiced sounds, there is reduced articulatory precision due to air escaping through the nasal cavity. However, the acoustic manifestation of these symptoms is highly variable, making hypernasality estimation very challenging, both for human specialists and automated systems. Previous work in this area relies on either engineered features based on statistical signal processing or machine learning models trained on clinical ratings. Engineered features often fail to capture the complex acoustic patterns associated with hypernasality, whereas metrics based on machine learning are prone to overfitting to the small disease-specific speech datasets on which they are trained. Here we propose a new set of acoustic features that capture these complementary dimensions. The features are based on two acoustic models trained on a large corpus of healthy speech. The first acoustic model aims to measure nasal resonance from voiced sounds, whereas the second acoustic model aims to measure articulatory imprecision from unvoiced sounds. To demonstrate that the features derived from these acoustic models are specific to hypernasal speech, we evaluate them across different dysarthria corpora. Our results show that the features generalize even when training on hypernasal speech from one disease and evaluating on hypernasal speech from another disease (e.g., training on Parkinson's disease, evaluation on Huntington's disease), and when training on neurologically disordered speech but evaluating on cleft palate speech.