PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 12237054

Pathological voice quality assessment using artificial neural networks.

R T Ritchings·M McGillion·C J Moore
View original source ↗Export metadata ↓

Abstract

This paper describes a prototype system for the objective assessment of voice quality in patients recovering from various stages of laryngeal cancer. A large database of male subjects steadily phonating the vowel /i/ was used in the study, and the quality of their voices was independently assessed by a speech and language therapist (SALT) according to their seven-point ranking of subjective voice quality. The system extracts salient short-term and long-term time-domain and frequency-domain parameters from impedance (EGG) signals and these are used to train and test an artificial neural network (ANN). Multi-layer perceptron (MLP) ANNs were investigated using various combinations of these parameters, and the best results were obtained using a combination of short-term and long-term parameters, for which an accuracy of 92% was achieved. It is envisaged that this system could be used as an assessment tool, providing a valuable aid to the SALT during clinical evaluation of voice quality.

Explore related subjects

Acoustic Impedance TestsFemaleHumansLaryngeal NeoplasmsMaleNeural Networks, ComputerReproducibility of ResultsSensitivity and SpecificitySpeech AcousticsSpeech DisordersSpeech Production MeasurementVoice QualityJournal ArticleResearch Support, Non-U.S. Gov'tValidation Study

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

R T Ritchings, M McGillion, C J Moore. Pathological voice quality assessment using artificial neural networks.. https://doi.org/10.1016/s1350-4533(02)00064-4

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2007

Bayesian estimation of intervention effect with pre- and post-misclassified binomial data.

We consider studies in which an enrolled subject tests positive on a fallible test. After an intervention, disease status is re-diagnosed with the same fallible instrument. Potential misclassification in the diagnostic test causes regression to the mean that biases inferences about the true intervention effect. The existing likelihood approach suffers in situations where either sensitivity or specificity is near 1. In such cases, common in many diagnostic tests, confidence interval coverage can often be below nominal for the likelihood approach. Another potential drawback of the maximum likelihood estimator (MLE) method is that it requires validation data to eliminate identification problems. We propose a Bayesian approach that offers improved performance in general, but substantially better performance than the MLE method in the realistic case of a highly accurate diagnostic test. We obtain this superior performance using no more information than that employed in the likelihood method. Our approach is also more flexible, doing without validation data if necessary, but accommodating multiple sources of information, if available, thereby systematically eliminating identification problems. We show via a simulation study that our Bayesian approach outperforms the MLE method, especially when the diagnostic test has high sensitivity, specificity, or both. We also consider a real data example for which the diagnostic test specificity is close to 1 (false positive probability close to 0).

Acoustic Impedance Tests↗
PubMed2006

Abnormal electronystagmography in rheumatoid arthritis.

OBJECTIVE: Although sensorineural hearing loss has been widely investigated in those with rheumatoid arthritis, studies assessing the vestibular system in patients with rheumatoid arthritis are limited. The aim of this study was to assess the vestibular system in patients with rheumatoid arthritis. METHODS: The study consisted of 43 patients with rheumatoid arthritis and 30 healthy controls. Otorhinolaryngologic and neurotologic examinations, pure-tone audiometry, impedancemetry, electronystagmography including smooth pursuit, saccade, positional, and caloric tests were performed in all patients with rheumatoid arthritis and in controls. The erythrocyte sedimentation rate, C-reactive protein level, and rheumatoid factor level were evaluated in all patients with rheumatoid arthritis. RESULTS: Audiograms revealed sensorineural hearing loss in 12 patients (27.9%) with rheumatoid arthritis and in two controls (6.6%); the difference was statistically significant (P=.033). In those with rheumatoid arthritis, the results of electronystagmography revealed central abnormalities in nine patients (20.9%), peripheral abnormalities in three (6.9%), and mixed abnormalities in three (6.9%). Smooth pursuit and saccade tracing impairments were significantly higher in patients with rheumatoid arthritis (P>.05). Canal paresis in patients with rheumatoid arthritis were significantly higher than those in the control group (P=.039). No association was found between electronystagmographic abnormalities in patients with rheumatoid arthritis and age, sex, duration of disease, the results of laboratory testing, sensorineural hearing loss, or medication use. CONCLUSION: Our results suggest an association of rheumatoid arthritis with vestibular system dysfunction as well as auditory impairment.

Acoustic Impedance Tests↗
PubMed2006

Reproducibility of sonotubometry as Eustachian tube ventilatory function test in healthy children.

OBJECTIVES: To devise a simple and reliable diagnostic procedure to test Eustachian tube function routinely in an ENT outpatient setting. One method to measure ET ventilatory function is sonotubometry. The reproducibility of a recently updated sonotubometry set-up was tested in healthy children. METHODS: The test population comprised 61 school children aged from 6 to 8 years. Only otologically healthy children were included. Health state was established by means of a 12-item questionnaire. To test reproducibility, sonotubometric testing took place in two sessions of 10 acts of swallowing each. Spearman's coefficient was used to test the correlation between the two sets of measurements. All testing took place at a primary school in a nearby village. RESULTS: Opening of the ET was recorded in at least one of the two measurement sessions in 82% of the children. The first and second sessions were highly correlated, with a Spearman's coefficient of 0.89. CONCLUSIONS: In otologically healthy children, opening of the ET was recorded frequently using the updated sonotubometry set-up. Measurement results had high reproducibility. Therefore, the test forms a useful method to assess ET ventilatory function in otologically healthy children. The performance of this updated version needs to be established in children with otological diseases.

Acoustic Impedance Tests↗