China
Africa
Explore chapters and articles related to this topic
The Evolution of Anticancer Therapies
Published in David E. Thurston, Ilona Pysz, Chemistry and Pharmacology of Anticancer Drugs, 2021
Artificial Intelligence (AI) is entering every aspect of daily life, ranging from Alexa-type devices in our homes to voice recognition systems used when calling banks. The continued rapid growth in computer-processing power over the past two decades, the development of advanced algorithms, and the availability of large data sets have driven major improvements in machine learning. This has helped to introduce “narrow” AI technologies which focus on specific tasks such as improved abilities to analyze, understand, and generate speech and text through techniques called natural-language processing. Artificial neural networks have also been introduced that are designed to simulate the way our brains make sense of the world and learn from past experiences. These techniques are already in widespread use in areas such as traffic route selection, voice analysis, medical diagnostic systems, and computer vision.
Assessment and Examination of the Larynx
Published in John C Watkinson, Raymond W Clarke, Terry M Jones, Vinidh Paleri, Nicholas White, Tim Woolford, Head & Neck Surgery Plastic Surgery, 2018
Jean-Pierre Jeannon, Enyinnaya Ofo
The rigid Hopkins rod system uses 70- or 90-degree angled lenses and allows an excellent view of the larynx through a transoral approach. This is the favoured technique for laryngologists in the ‘voice clinic’ as the wider rigid rod lens produces a much higher optical resolution for more detailed assessment of phonation.13 Laryngoscopy can be supplemented with stroboscopy, laryngography or digital acoustic voice analysis (see Chapter 62, Evaluation of the voice).
Gender dysphoria and the larynx
Published in Declan Costello, Guri Sandhu, Practical Laryngology, 2015
Christella Antoni, Guri Sandhu
Unfortunately, there are no studies looking at the long-term results of these various surgical approaches. There certainly needs to be better reporting of outcomes with objective assessment tools. One of the difficulties of being a specialist centre is that patients travel great distances to attend and it is usually patients with successful surgical outcomes who are most reluctant to return for voice analysis. It is fortunate that most transgender patients achieve appropriate voices through their own efforts or assisted by the speech therapist. Surgery for pitch elevation is currently not perfected. The ideal surgical procedure would shorten and reduce the bulk of the male vocal cords, with appropriate pitch elevation, maintained permanently. It would also be carried out endoscopically to avoid scars. Further surgical advances need to be made in the field of laryngology before this is possible.
Acoustic analysis of voice in bulbar amyotrophic lateral sclerosis: a systematic review and meta-analysis of studies
Published in Logopedics Phoniatrics Vocology, 2020
Rita Chiaramonte, Marco Bonfiglio
Neurological and ENT (Ear, Nose, and Throat) examination of patients with ALS grossly shows difficulty in production of short phrases, inappropriate pauses, hypernasality, strain-strangled voice. The degree of speech intelligibility must not be underestimated because it reduces the quality of life and the ability to communicate leads to social isolation. Speech impairments are prognostic factors for survival time in patients with ALS [4]. Instrumented voice analysis allows a more precise estimation of voice-related changes with quantitative parameters and repeatable measures and an early identification in order to design supportive interventions and predict progression of the disease and prognosis [4–6]. For this reason, voice analysis seems to be a useful tool to obtain more specific and subclinical information about the progression of the pathologic processes to ALS.
The cut-off analysis using visual analogue scale and cepstral assessments on severity of voice disorder
Published in Logopedics Phoniatrics Vocology, 2018
Yeon Woo Lee, Geun Hyo Kim, In Ho Bae, Hee June Park, Soo Geun Wang, Soon Bok Kwon
Although these auditory-perceptual assessments demonstrated high inter- and intra-rater reliability, they are subjective and, thus, conducting acoustic measurements, such as CPP analysis, can help to determine severity of voice disorder [22–24]. In this study, we also implemented acoustic analyses to determine the CPP cut-off points according to the severity of voice disorder. The cut-off points we attained, 7.050, 4.651, and 2.989, indicate that increased vocal severity/abnormality is associated with a decrease in CPP points, consistent with previous studies [4,25–27]. These previous studies measured CPP and predicted severity of voice disorder via regression analysis; however, no previous studies have analyzed CPP cut-off values according to severity of voice disorder or the diagnostic accuracy of these cut-off values. In our study, CPP cut-off points showed high sensitivity and AUC. Similar to our results for VAS, the AUC and sensitivity values, representing the ability to detect a disorder, increased with severity of voice disorder, indicating that reliable voice analysis is possible using CPP, regardless of severity of voice disorder [28]. Although the results of this study cannot be generalized, given that CPP points varied dependent on the type of voice samples, it is meaningful to measure cut-off points of CPP according to degree of severity and confirm the AUC and sensitivity values increased with severity of voice disorder in CPP analysis.
Automatic voice analysis for dysphagia detection
Published in Speech, Language and Hearing, 2018
K. López-de-Ipiña, P. Calvo, M. Faundez-Zanuy, P. Clavé, W. Nascimento, U. Martinez de Lizarduy, D. Alvarez, V. Arreola, O. Ortega, Jiri Mekyska, P. Sanz-Cartagena
This work presents results of an experiment designed to detect speech alterations in dysphagia evaluation based on automatic analysis of speech features. The results indicated a high degree of accuracy in detecting voice associated with basal and viscosity states. The detection accuracy increased with a corresponding increase in the number of speech features considered. A major advantage of voice analysis is its low intrusiveness and easy implementation in clinical practice. Thus, while the gold standard of dysphagia diagnosis continues to involve video-fluoroscopy analysis, the consideration of voice analysis may prove to be a far simpler and less invasive approach to diagnosis. Clearly, more work in this area needs to be performed. However the present results may lead to new less-invasive methodologies to diagnose deglutition issues.