Evaluation of noise excitation as a method for detection of hypernasality

Young, Kat; Sweeney, Triona; Vos, Rebecca R.; Mehendale, Felicity V.; Daffern, Helena

doi:10.1016/j.apacoust.2022.108639

Cited by 3 publications

(2 citation statements)

References 42 publications

(93 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To remove outliers caused by random noise, the ratios R(ω, ϕ) of specifical frequencies ω ordered on the frame axis from smallest to largest and are denoted as R (ω, γ), where γ is the ranking position of the specified frequency. The average of the values located between the upper quartiles and lower quartiles is taken as the average power spectral density ratio, as shown in (6).…”

Section: Calculation Of the Average Power Spectral Density Ratio Of T...mentioning

confidence: 99%

“…According to the causes of the disease, VPI can be classified as congenital VPI or acquired VPI [ 5 ]. Congenital developmental malformations, such as cleft palate [ 6 ] and congenital myotonic dystrophy [ 7 ], can lead to congenital VPI. In terms of acquired VPI, tonsillectomy [ 8 ], adenoidectomy [ 9 ], palatal sail shortening, or trauma [ 10 ] can cause it.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Zhang,

et al. 2023

Diagnostics

View full text Add to dashboard Cite

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.

show abstract

Section: Calculation Of the Average Power Spectral Density Ratio Of T...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

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

Zhang,

et al. 2023

Diagnostics

View full text Add to dashboard Cite

show abstract

Three‐dimensional reconstruction of King Henri IV's paranasal sinuses and mastoid cells

Baudouin,

Amelot,

Huynh‐Charlier

et al. 2024

Clinical Anatomy

View full text Add to dashboard Cite

PurposeThe preserved head of King Henri IV of France (life 1553–1610, reign 1589–1610) has survived to the present day thanks to high‐quality embalming and favorable conservation conditions. The aim of this study was to examine Henry IV's upper resonant cavities and mastoids using an original and innovative forensic three‐dimensional segmentation method.MethodsThe paranasal sinuses and mastoid cells of King Henri IV of France were studied by cross‐referencing available biographical information with clinical and flexible endoscopic examination and computed tomography (CT‐scan) imaging. The paranasal sinuses and mastoid cells were delineated and their volumes were assessed using ITK‐SNAP 4.0 software (open‐source). Graphical representations were created using Fusion 360® (Autodesk Inc., San Rafael, CA, USA) and MeshMixer® (Autodesk Inc., San Rafael, CA, USA).ResultsParanasal sinus tomodensitometry revealed abnormalities in shape and number. Henri IV of France suffered from sinus aplasia. Neither the left sphenoid nor left frontal sinus contrasted sharply, and a remarkable pneumatization of the right clinoid processes extended throughout the height of the right pterygoid process. The total volumes of Henri IV's mastoid air‐cells were estimated at 27 and 26 mL, respectively, for the right and left sides, exceeding the normal mean and the maximum of modern subjects by a wide margin. No sign of chronic ear or sinus condition was found.ConclusionsAn innovative method has been developed in forensic medicine to establish hypotheses about the growth and respiratory conditions of the face.

show abstract