BioVoice: A multipurpose tool for voice analysis

Morelli, Maria Sole; Orlandi, Silvia; Manfredi, Claudia

doi:10.1016/j.bspc.2020.102302

Cited by 10 publications

(8 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Italian word /a’jwɔle/ was manually segmented from the standardized sentence and analyzed with the BioVoice open-source software tool [ 22 , 23 ], already successfully applied to the acoustical analysis of voices from newborns to children and adults, such as shape classification of newborn cry melody [ 24 ], dysprosody detection in Parkinson’s disease [ 25 ], and genetic syndrome speech phenotype characterization [ 26 ]. The word /a’jwɔle/ is widely used as it is mainly composed of vowels and is also suited for studying articulation capabilities.…”

Section: Methodsmentioning

confidence: 99%

Machine Learning Assessment of Spasmodic Dysphonia Based on Acoustical and Perceptual Parameters

et al. 2023

Self Cite

View full text Add to dashboard Cite

Adductor spasmodic dysphonia is a type of adult-onset focal dystonia characterized by involuntary spasms of laryngeal muscles. This paper applied machine learning techniques for the severity assessment of spasmodic dysphonia. To this aim, 7 perceptual indices and 48 acoustical parameters were estimated from the Italian word /a’jwɔle/ emitted by 28 female patients, manually segmented from a standardized sentence and used as features in two classification experiments. Subjects were divided into three severity classes (mild, moderate, severe) on the basis of the G (grade) score of the GRB scale. The first aim was that of finding relationships between perceptual and objective measures with the Local Interpretable Model-Agnostic Explanations method. Then, the development of a diagnostic tool for adductor spasmodic dysphonia severity assessment was investigated. Reliable relationships between G; R (Roughness); B (Breathiness); Spasmodicity; and the acoustical parameters: voiced percentage, F2 median, and F1 median were found. After data scaling, Bayesian hyperparameter optimization, and leave-one-out cross-validation, a k-nearest neighbors model provided 89% accuracy in distinguishing patients among the three severity classes. The proposed methods highlighted the best acoustical parameters that could be used jointly with GRB indices to support the perceptual evaluation of spasmodic dysphonia and provide a tool to help severity assessment of spasmodic dysphonia.

show abstract

Section: Methodsmentioning

confidence: 99%

Machine Learning Assessment of Spasmodic Dysphonia Based on Acoustical and Perceptual Parameters

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…Stability in vibrato rate (VR) and VE is dependent on stable oscillatory mechanisms and fine intralaryngeal muscle coordination [42][43][44]. Morelli and colleagues [45] presented the BioVoice voice-analysis software that includes two measures for singing voice vibrato perturbation analysis: vibrato jitter and vibrato shimmer (hereafter V Jitt and V Shim ). Like the well-known jitter and shimmer measures that measure frequency and amplitude perturbation in the acoustic waveform, V Jitt and V Shim quantify perturbation in the f o vibrato waveform of a sung sample (for V Jitt and V Shim equations see [46]).…”

Section: Instrumental Analysis Of the Singing Voicementioning

confidence: 99%

“…The RAP and APQ3 were obtained in the 'voice report' function of PRAAT using standard settings. The freeware BioVoice [45] was used to calculate two measures of vibrato regularity for each signal: V Jitt and V Shim . Numerical results were saved in an Excel file after automatic analysis and then integrated into the combined data set.…”

Section: Acoustic Data Processingmentioning

confidence: 99%

It Sounds like It Feels: Preliminary Exploration of an Aeroacoustic Diagnostic Protocol for Singers

Baker

Purdy

Rakena

et al. 2023

JCM

View full text Add to dashboard Cite

To date, no established protocol exists for measuring functional voice changes in singers with subclinical singing-voice complaints. Hence, these may go undiagnosed until they progress into greater severity. This exploratory study sought to (1) determine which scale items in the self-perceptual Evaluation of Ability to Sing Easily (EASE) are associated with instrumental voice measures, and (2) construct as proof-of-concept an instrumental index related to singers’ perceptions of their vocal function and health status. Eighteen classical singers were acoustically recorded in a controlled environment singing an /a/ vowel using soft phonation. Aerodynamic data were collected during a softly sung /papapapapapapa/ task with the KayPENTAX Phonatory Aerodynamic System. Using multi and univariate linear regression techniques, CPPS, vibrato jitter, vibrato shimmer, and an efficiency ratio (SPL/PSub) were included in a significant model (p < 0.001) explaining 62.4% of variance in participants’ composite scores of three scale items related to vocal fatigue. The instrumental index showed a significant association (p = 0.001) with the EASE vocal fatigue subscale overall. Findings illustrate that an aeroacoustic instrumental index may be useful for monitoring functional changes in the singing voice as part of a multidimensional diagnostic approach to preventative and rehabilitative voice healthcare for professional singing-voice users.

show abstract

“…Research studies published in the last few years focused on the identification of the acoustic cry features ( LaGasse et al, 2005 ; Manfredi et al, 2018 ) to study the well-being of the newborns, neonatal diseases ( Lawford et al, 2022 ) and neurodevelopmental disorders ( Esposito and Venuti, 2010 ) through signal processing and Artificial Intelligence (AI) techniques ( Farsaie Alaie and Tadj, 2012 ; Zabidi et al, 2018 ; Morelli et al, 2021 ). Acoustic cry features include fundamental frequency (F0) ( Porter et al, 1988 ), resonance frequencies (F1-F3) related to vocal tract maturation, parameters of vibrato rate and extent (jitter and shimmer), and noise levels ( Wermke et al, 2002 ).…”

Section: Introductionmentioning

confidence: 99%

How can cry acoustics associate newborns’ distress levels with neurophysiological and behavioral signals?

Laguna,

Pusil,

Acero-Pousa

et al. 2023

Front. Neurosci.

Self Cite

View full text Add to dashboard Cite

IntroductionEven though infant crying is a common phenomenon in humans’ early life, it is still a challenge for researchers to properly understand it as a reflection of complex neurophysiological functions. Our study aims to determine the association between neonatal cry acoustics with neurophysiological signals and behavioral features according to different cry distress levels of newborns.MethodsMultimodal data from 25 healthy term newborns were collected simultaneously recording infant cry vocalizations, electroencephalography (EEG), near-infrared spectroscopy (NIRS) and videos of facial expressions and body movements. Statistical analysis was conducted on this dataset to identify correlations among variables during three different infant conditions (i.e., resting, cry, and distress). A Deep Learning (DL) algorithm was used to objectively and automatically evaluate the level of cry distress in infants.ResultsWe found correlations between most of the features extracted from the signals depending on the infant’s arousal state, among them: fundamental frequency (F0), brain activity (delta, theta, and alpha frequency bands), cerebral and body oxygenation, heart rate, facial tension, and body rigidity. Additionally, these associations reinforce that what is occurring at an acoustic level can be characterized by behavioral and neurophysiological patterns. Finally, the DL audio model developed was able to classify the different levels of distress achieving 93% accuracy.ConclusionOur findings strengthen the potential of crying as a biomarker evidencing the physical, emotional and health status of the infant becoming a crucial tool for caregivers and clinicians.

show abstract

BioVoice: A multipurpose tool for voice analysis

Cited by 10 publications

References 34 publications

Machine Learning Assessment of Spasmodic Dysphonia Based on Acoustical and Perceptual Parameters

Machine Learning Assessment of Spasmodic Dysphonia Based on Acoustical and Perceptual Parameters

It Sounds like It Feels: Preliminary Exploration of an Aeroacoustic Diagnostic Protocol for Singers

How can cry acoustics associate newborns’ distress levels with neurophysiological and behavioral signals?

Contact Info

Product

Resources

About