Nasometry, videofluoroscopy, and the speech pathologist's evaluation and treatment

Automatic Detection System for Velopharyngeal Insufficiency Based on Acoustic Signals from Nasal and Oral Channels

Velopharyngeal insufficiency (VPI) is a type of pharyngeal function dysfunction that causes speech impairment and swallowing disorder. Speech therapists play a key role on the diagnosis and treatment of speech disorders. However, there is a worldwide shortage of experienced speech therapists. Artificial intelligence-based computer-aided diagnosing technology could be a solution for this. This paper proposes an automatic system for VPI detection at the subject level. It is a non-invasive and convenient approach for VPI diagnosis. Based on the principle of impaired articulation of VPI patients, nasal- and oral-channel acoustic signals are collected as raw data. The system integrates the symptom discriminant results at the phoneme level. For consonants, relative prominent frequency description and relative frequency distribution features are proposed to discriminate nasal air emission caused by VPI. For hypernasality-sensitive vowels, a cross-attention residual Siamese network (CARS-Net) is proposed to perform automatic VPI/non-VPI classification at the phoneme level. CARS-Net embeds a cross-attention module between the two branches to improve the VPI/non-VPI classification model for vowels. We validate the proposed system on a self-built dataset, and the accuracy reaches 98.52%. This provides possibilities for implementing automatic VPI diagnosis.

Tratamiento de la nasalidad transpalatal en un caso complejo con trastorno fonológico

Se presenta el proceso de evaluación e intervención logopédica en una niña de 9 años con hipernasalidad y dificultades fonológicas perceptivas y expresivas. Se evalúo el nivel fonético y fonológico del lenguaje, el timbre nasal mediante nasometría, la integridad funcional de las estructuras velopalatofaríngeas y la audición. La paciente pronunciaba los sonidos [d], [l] y [t] muy distorsionados y con características de [n], al tiempo que no era capaz de distinguirlos de la consonante nasal. La configuración de su cavidad oral y su base articulatoria idiosincrática favorecía el fenómeno de nasalidad transpalatal: presencia excesiva de resonancia nasal durante la emisión de sonidos no nasales en ausencia de disfunción velofaríngea. Para el abordaje de la hipernasalidad se aplicó un tratamiento intensivo con la herramienta de biofeedback visual Nasometer II, como recomienda la literatura existente para los casos de nasalidad de origen funcional. El tratamiento fue eficaz para el control voluntario de la reducción de la hiperrinolalia, pero no fue efectivo debido a que la paciente no fue capaz de reducir el timbre nasal en el uso espontáneo del habla.

Paediatric velopharyngeal insufficiency following adenotonsillar surgery

OBJECTIVE

Paediatric velopharyngeal insufficiency (VPI) is a known but rare complication following adenotonsillar surgery that can have significant adverse effects on the communication as well as psychological well-being of the patient and their family. We sought to assess risk factors, aetiology, assessment and management of these patients through a dedicated multidisciplinary clinic.

METHODS

Retrospective data collection was performed for patients seen in the Great Ormond Street Hospital for Children multidisciplinary VPI clinic from the 1^st of January 2015 until 30^th of April 2020. Paediatric patients with previous adenotonsillar surgery and no evidence of cleft palate or speech and language disorder were included in the study.

RESULTS

29 patients met the inclusion criteria, with 16 having previous adenotonsillectomy and 13 isolated adenoidectomy. In our VPI clinic, patients were seen on average for 4.9 occasions over a 38.3-month period. Clinical assessment was conducted using GOS.SP.ASS '98 speech assessment tool, speech videofluoroscopy and nasoendoscopy, as per individual needs. The main cause of post-adenoidectomy VPI was identified in 72.5% of the cases. Speech videofluoroscopy was performed in 27 cases. Associated anatomic features identified included deep pharynx (37%), long palate (22.2%) and variable levator position. Severe hypernasality was noted in 3 patients, while in 20 cases moderate or mild hypernasality was found. There were no patients with normal speech. Ten patients were treated with speech therapy alone, whereas surgical intervention was required in seventeen cases. In the population who received treatment and had adequately recorded follow-up, improvement in speech was noted in 86.9%, with 30.4% having oral resonance on last review. Of the patients with severe hypernasality, all improved but had some persistent hyper nasality on last clinic review.

CONCLUSIONS

We present our multidisciplinary management of post adenoidectomy VPI. Through the investigations in our dedicated specialist VPI clinic, the cause of VPI was found more frequently than in previous reports in the literature. Intense treatment is usually required with lengthy follow-up and multiple attendances in VPI clinic. Main modalities of management include SLT, surgery and speech prostheses. Most patients' speech will improve with intervention. We highlight the importance of early recognition, referral and a multi-disciplinary approach in treating this condition. We advise ENT surgeons to ensure patients are adequately aware of this complication given its potential impact.

OBJECTIVE MEASURES OF PLOSIVE NASALIZATION IN HYPERNASAL SPEECH

Hypernasal speech is a common symptom across several neurological disorders; however it has a variable acoustic signature, making it difficult to quantify acoustically or perceptually. In this paper, we propose the nasal cognate distinctiveness features as an objective proxy for hypernasal speech. Our method is motivated by the observation that incomplete velopharyngeal closure changes the acoustics of the resultant speech such that alveolar stops /t/ and /d/ map to the alveolar nasal /n/ and bilabial stops /b/ and /p/ map to bilabial nasal /m/. We propose a new family of features based on likelihood ratios between the plosives and their respective nasal cognates. These features are based on an acoustic model that is trained only on healthy speech, and evaluated on a set of 75 speakers diagnosed with different dysarthria subtypes and exhibiting varying levels of hypernasality. Our results show that the family of features compares favorably with the clinical perception of speech-language pathologists subjectively evaluating hypernasality.