Maria du Toit
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Maria du Toit has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Jeannie van der Linde
Department of Speech-Language Pathology and Audiology, University of Pretoria, South Africa
10 shared publications - Marien Alet Graham
University of South Africa
7 shared publications - Renata Eccles
University of Pretoria
6 shared publications Jeannie van der Linde
Department of Speech-Language Pathology and Audiology, University of Pretoria, Hatfield, Pretoria, South Africa
4 shared publicationsDe Wet Swanepoel
Department of Speech-Language Pathology and Audiology, University of Pretoria, Pretoria, South Africa
3 shared publications- De Wet Swanepoel
Department of Speech-Language Pathology and Audiology, University of Pretoria, South Africa
3 shared publications
Latest Publications
- Open Access
- 6 October 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Smartphone-Based Vocal Fatigue Detection: A Proof-of-Concept Study (Preprint)
BACKGROUND Vocal fatigue is a common functional voice complaint among occupational voice users and is typically assessed using self-report and clinical evaluation in controlled settings. These approaches do not capture dynamic fatigue-related voice changes that occur during everyday voice use. Advances in mobile health (mHealth) and machine learning provide opportunities for smartphone-based voice monitoring; however, environmental noise remains a major challenge for real-world deployment. OBJECTIVE This study aimed to evaluate the technical feasibility and noise robustness of a smartphone-compatible system for detecting vocal fatigue–related voice changes under controlled but ecologically relevant acoustic conditions. METHODS A proof-of-concept system integrating voice isolation, acoustic feature extraction, and machine learning–based classification was developed for smartphone deployment. Voice recordings were obtained from a single speaker under fatigued and nonfatigued conditions and augmented with 12 real-world background noise recordings from 10 everyday environments at signal-to-noise ratios (SNRs) ranging from −10 dB to 30 dB. System performance was evaluated at the subsystem and end-to-end levels, including noise attenuation, feature extraction accuracy relative to reference software, classification accuracy across SNR conditions, and computational feasibility on mobile-compatible hardware. RESULTS Within this single-speaker proof-of-concept dataset, the complete system achieved an overall vocal fatigue classification accuracy of 85.81%, with balanced classification performance metrics, including precision (0.856), recall/sensitivity (0.861), and specificity (0.855). Classification accuracy remained above 80% at SNRs of −5 dB and higher, decreasing to 78.67% at −10 dB SNR. The voice isolation module achieved an average noise attenuation of 56.62 dB across SNR conditions, with consistent suppression within the human vocal range. Acoustic feature extraction demonstrated high agreement with reference software, achieving average accuracy above 88% at −10 dB SNR and above 90% at higher SNRs. In a smartphone-server configuration, in which audio recorded on the smartphone was processed on a cloud server, end-to-end processing took 8.38 seconds per sample (excluding data transmission), indicating feasibility for short-latency periodic mobile monitoring. CONCLUSIONS This proof-of-concept study demonstrates the technical feasibility of smartphone-based detection of speaker-specific fatigue-related voice changes under a range of noisy conditions. While performance declined under extreme noise, results support the potential of mHealth voice monitoring systems for tracking vocal fatigue outside the clinic. Further validation across multiple speakers and with clinically anchored outcome measures is required prior to clinical application. CLINICALTRIAL N/a
- 6 October 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessSmartphone-Based Vocal Fatigue Detection: A Proof-of-Concept Study (Preprint)
BACKGROUND Vocal fatigue is a common functional voice complaint among occupational voice users and is typically assessed using self-report and clinical evaluation in controlled settings. These approaches do not capture dynamic fatigue-related voice changes that occur during everyday voice use. Advances in mobile health (mHealth) and machine learning provide opportunities for smartphone-based voice monitoring; however, environmental noise remains a major challenge for real-world deployment. OBJECTIVE This study aimed to evaluate the technical feasibility and noise robustness of a smartphone-compatible system for detecting vocal fatigue–related voice changes under controlled but ecologically relevant acoustic conditions. METHODS A proof-of-concept system integrating voice isolation, acoustic feature extraction, and machine learning–based classification was developed for smartphone deployment. Voice recordings were obtained from a single speaker under fatigued and nonfatigued conditions and augmented with 12 real-world background noise recordings from 10 everyday environments at signal-to-noise ratios (SNRs) ranging from −10 dB to 30 dB. System performance was evaluated at the subsystem and end-to-end levels, including noise attenuation, feature extraction accuracy relative to reference software, classification accuracy across SNR conditions, and computational feasibility on mobile-compatible hardware. RESULTS Within this single-speaker proof-of-concept dataset, the complete system achieved an overall vocal fatigue classification accuracy of 85.81%, with balanced classification performance metrics, including precision (0.856), recall/sensitivity (0.861), and specificity (0.855). Classification accuracy remained above 80% at SNRs of −5 dB and higher, decreasing to 78.67% at −10 dB SNR. The voice isolation module achieved an average noise attenuation of 56.62 dB across SNR conditions, with consistent suppression within the human vocal range. Acoustic feature extraction demonstrated high agreement with reference software, achieving average accuracy above 88% at −10 dB SNR and above 90% at higher SNRs. In a smartphone-server configuration, in which audio recorded on the smartphone was processed on a cloud server, end-to-end processing took 8.38 seconds per sample (excluding data transmission), indicating feasibility for short-latency periodic mobile monitoring. CONCLUSIONS This proof-of-concept study demonstrates the technical feasibility of smartphone-based detection of speaker-specific fatigue-related voice changes under a range of noisy conditions. While performance declined under extreme noise, results support the potential of mHealth voice monitoring systems for tracking vocal fatigue outside the clinic. Further validation across multiple speakers and with clinically anchored outcome measures is required prior to clinical application. CLINICALTRIAL N/a
- Open Access
- 26 August 2026
- Published by Elsevier in Journal of Voice
Feasibility of Low-Cost Smartphone Endoscopy for Laryngeal Imaging
- 26 August 2026
- Published by Elsevier in Journal of Voice
Open AccessFeasibility of Low-Cost Smartphone Endoscopy for Laryngeal Imaging
- Open Access
- 14 July 2026
- Published by Elsevier in Journal of Voice
Who Benefits Most From Voice Use Reduction? Baseline Predictors Of Vocal Fatigue Improvement In Occupational Voice Users.
- 14 July 2026
- Published by Elsevier in Journal of Voice
Open AccessWho Benefits Most From Voice Use Reduction? Baseline Predictors Of Vocal Fatigue Improvement In Occupational Voice Users.
- Open Access
- 24 March 2026
- Published by Elsevier in Journal of Voice
MHealth Technologies in Voice Disorders: A Scoping Review
- 24 March 2026
- Published by Elsevier in Journal of Voice
Open AccessMHealth Technologies in Voice Disorders: A Scoping Review
- Open Access
- 8 January 2026
- Published by SAGE Publications in Journal of Early Childhood Research
Adaptation of a developmental milestone resource for parents from diverse, low-income communities in South Africa
Knowledge of developmental milestones allows parents to support the developmental needs of their children and monitor their behaviour. Many available developmental resources, however, do not apply to culturally, economically, and linguistically diverse communities in low– and middle-income countries. There is a need to adapt established resources to improve contextual relevance. As primary stakeholders, parents should contribute to the adaptations. An existing developmental milestone resource was adapted for parents from low-income communities in South Africa using a mixed-method research design. In phases 1 and 2, a six-member expert panel reviewed and adapted the existing resource for the parents of children aged 2–47 months using a questionnaire and focus group. In phase 3, 18 parents of young children from low-income communities were interviewed to gain their perspectives on the adapted milestone. Most developmental milestones were deemed applicable, but they require adaptation to be relevant for use in low-income communities. The four themes identified were: language use, access to materials indicated in the resource, context and developmental literacy. Parents found the adapted resource relevant to promoting developmental literacy. International developmental milestone resources require contextual adaptation for diverse communities. Parents were included in developing the resource, increasing its relevance. The adapted resource should be trialled to evaluate the effectiveness of promoting parents’ developmental literacy.
- 8 January 2026
- Published by SAGE Publications in Journal of Early Childhood Research
Open AccessAdaptation of a developmental milestone resource for parents from diverse, low-income communities in South Africa
Knowledge of developmental milestones allows parents to support the developmental needs of their children and monitor their behaviour. Many available developmental resources, however, do not apply to culturally, economically, and linguistically diverse communities in low– and middle-income countries. There is a need to adapt established resources to improve contextual relevance. As primary stakeholders, parents should contribute to the adaptations. An existing developmental milestone resource was adapted for parents from low-income communities in South Africa using a mixed-method research design. In phases 1 and 2, a six-member expert panel reviewed and adapted the existing resource for the parents of children aged 2–47 months using a questionnaire and focus group. In phase 3, 18 parents of young children from low-income communities were interviewed to gain their perspectives on the adapted milestone. Most developmental milestones were deemed applicable, but they require adaptation to be relevant for use in low-income communities. The four themes identified were: language use, access to materials indicated in the resource, context and developmental literacy. Parents found the adapted resource relevant to promoting developmental literacy. International developmental milestone resources require contextual adaptation for diverse communities. Parents were included in developing the resource, increasing its relevance. The adapted resource should be trialled to evaluate the effectiveness of promoting parents’ developmental literacy.
- Open Access
- 17 July 2025
- Published by AOSIS in South African Journal of Childhood Education
- Vol. 15 (1) , 11
Developing a contextually relevant ECD milestone guide for South African practitioners
Background: Two hundred and fifty million children under five in low- and middle-income countries are at risk of not achieving their developmental potential. High-quality milestone guides can help mitigate these risks but are often not contextually appropriate for countries like South Africa, because of unavailable resources and its inappropriateness in multilingual group contexts. Aim: This study aimed to develop and pilot a contextually relevant ECD milestone guide for practitioners working with preschool children (3–5 years 11 months) in low-resourced South African communities. Setting: This study focused on ECD practitioners within low-resourced South African communities. Methods: Data collection involved four phases: (1) An initial questionnaire and an abridged milestone guide were reviewed by an expert panel, who suggested contextual adaptations and activities, (2) The Delphi method was used to rank suggestions, (3) Virtual focus group addressed six milestones that required further consensus, (4) a pilot of the language and communication domain was conducted where six practitioners provided feedback on its usability. Results: Practitioners found the milestone guide valuable and usable, supporting their work with young children in low-resourced communities. Feedback informed further refinements to improve usability and contextual relevance. Conclusion: The adapted milestone guide equipped practitioners in low-resourced ECD classrooms with tools to promote age-appropriate development and identify developmental delays early. By addressing these delays, the guide helps break cycles of disadvantage, enabling children to thrive and reach their full potential. Contribution: This study offers a framework for developing contextually relevant milestone guides to support ECD practitioners in low-resourced settings.
- 17 July 2025
- Published by AOSIS in South African Journal of Childhood Education
- Vol. 15 (1) , 11
Open AccessDeveloping a contextually relevant ECD milestone guide for South African practitioners
Background: Two hundred and fifty million children under five in low- and middle-income countries are at risk of not achieving their developmental potential. High-quality milestone guides can help mitigate these risks but are often not contextually appropriate for countries like South Africa, because of unavailable resources and its inappropriateness in multilingual group contexts. Aim: This study aimed to develop and pilot a contextually relevant ECD milestone guide for practitioners working with preschool children (3–5 years 11 months) in low-resourced South African communities. Setting: This study focused on ECD practitioners within low-resourced South African communities. Methods: Data collection involved four phases: (1) An initial questionnaire and an abridged milestone guide were reviewed by an expert panel, who suggested contextual adaptations and activities, (2) The Delphi method was used to rank suggestions, (3) Virtual focus group addressed six milestones that required further consensus, (4) a pilot of the language and communication domain was conducted where six practitioners provided feedback on its usability. Results: Practitioners found the milestone guide valuable and usable, supporting their work with young children in low-resourced communities. Feedback informed further refinements to improve usability and contextual relevance. Conclusion: The adapted milestone guide equipped practitioners in low-resourced ECD classrooms with tools to promote age-appropriate development and identify developmental delays early. By addressing these delays, the guide helps break cycles of disadvantage, enabling children to thrive and reach their full potential. Contribution: This study offers a framework for developing contextually relevant milestone guides to support ECD practitioners in low-resourced settings.
- Open Access
- 6 January 2025
- Published by AOSIS in South African Journal of Communication Disorders
- Vol. 72 (1) , e1-e10
Developmental outcomes of small infants at a high-risk clinic: A short-term longitudinal study
Background: Small infants face more developmental risks than their full-term peers, necessitating early intervention and long-term monitoring. Objectives: This study examined the longitudinal developmental and hearing outcomes of small infants attending a high-risk clinic in a South African low-income community setting. Method: A short-term longitudinal within-subject descriptive study design was employed, where 28 participants underwent hearing and developmental screenings and assessments at two follow-up appointments (T1 and T2), at 6- and 12-month corrected age. Developmental outcomes, such as communication, motor and daily living skills, were evaluated using developmental screening tools (Parents Evaluation of Developmental Status [PEDS]), hearing screening (ABR MB11) and developmental assessments (Vineland-3). Results: All participants underwent hearing screening, with four (14.3%) failing twice (T1 and T2) and being referred for diagnostic evaluation. Developmental screening at T1 identified concerns in communication, gross motor and social-emotional skills (28.5%). Concerns persisted across T1 and T2 in the PEDS tool, with fine motor skills emerging as a key issue at T2. Vineland-3 assessments showed improvement from T1 to T2; initial concerns in daily living (M = 104.12; standard deviation [s.d.] = 38.99) and motor skills (M = 88.82; s.d. = 45.26) were no longer present at T2, where all participants had age-appropriate developmental scores. Conclusion: The findings highlight the need for comprehensive, routine developmental monitoring and early intervention to address delays in small infants. Continued follow-up care and support from birth to 12 months corrected age can improve outcomes and caregiver developmental literacy. Contribution: This study provides valuable insights for caregivers, healthcare policymakers and early intervention professionals by emphasising the importance of early screening, continuous monitoring and caregiver education in optimising developmental outcomes for small infants.
- 6 January 2025
- Published by AOSIS in South African Journal of Communication Disorders
- Vol. 72 (1) , e1-e10
Open AccessDevelopmental outcomes of small infants at a high-risk clinic: A short-term longitudinal study
Background: Small infants face more developmental risks than their full-term peers, necessitating early intervention and long-term monitoring. Objectives: This study examined the longitudinal developmental and hearing outcomes of small infants attending a high-risk clinic in a South African low-income community setting. Method: A short-term longitudinal within-subject descriptive study design was employed, where 28 participants underwent hearing and developmental screenings and assessments at two follow-up appointments (T1 and T2), at 6- and 12-month corrected age. Developmental outcomes, such as communication, motor and daily living skills, were evaluated using developmental screening tools (Parents Evaluation of Developmental Status [PEDS]), hearing screening (ABR MB11) and developmental assessments (Vineland-3). Results: All participants underwent hearing screening, with four (14.3%) failing twice (T1 and T2) and being referred for diagnostic evaluation. Developmental screening at T1 identified concerns in communication, gross motor and social-emotional skills (28.5%). Concerns persisted across T1 and T2 in the PEDS tool, with fine motor skills emerging as a key issue at T2. Vineland-3 assessments showed improvement from T1 to T2; initial concerns in daily living (M = 104.12; standard deviation [s.d.] = 38.99) and motor skills (M = 88.82; s.d. = 45.26) were no longer present at T2, where all participants had age-appropriate developmental scores. Conclusion: The findings highlight the need for comprehensive, routine developmental monitoring and early intervention to address delays in small infants. Continued follow-up care and support from birth to 12 months corrected age can improve outcomes and caregiver developmental literacy. Contribution: This study provides valuable insights for caregivers, healthcare policymakers and early intervention professionals by emphasising the importance of early screening, continuous monitoring and caregiver education in optimising developmental outcomes for small infants.
- Open Access
- 9 February 2024
- Published by Taylor & Francis in International Journal of Transgender Health
- Vol. 26 (3) , 750-764
Perceptions, knowledge, and perceived competencies of South African speech-language pathologists to render transgender voice and communication training
Speech-language pathologists (SLPs) receive extensive education and training on voice and voice disorders. Therefore, they are integral in rendering transgender voice and communication training (TVCT), as part of their scope of practice. Research has, however, identified a lack of confidence in SLPs to render this service due to a perceived lack of education, knowledge, and clinical exposure. To determine the perceptions, knowledge, and perceived competencies of South African SLPs regarding TVCT. A cross-sectional open online survey design using non-probability purposive and convenience sampling was used. Fully qualified, practicing South African SLPs were asked to volunteer to participate on social media platforms. Fifty-two valid data sets were recorded. Most participants agreed that TVCT falls within their scope of practice (n = 42, 84%), viewing it as their ethical responsibility (n = 40, 80%) as well as a necessity (n = 34, 68%). However, most participants reported feeling inadequately prepared to provide TVCT (n = 34, 68%) due to insufficient education and training in this field, with 23 participants (45.1%) reporting that they had not received any education or training on the topic. Participants generally held positive attitudes toward TVCT yet felt unprepared to render the service due to insufficient education, training, and exposure, revealing a crucial professional development need.
- 9 February 2024
- Published by Taylor & Francis in International Journal of Transgender Health
- Vol. 26 (3) , 750-764
Open AccessPerceptions, knowledge, and perceived competencies of South African speech-language pathologists to render transgender voice and communication training
Speech-language pathologists (SLPs) receive extensive education and training on voice and voice disorders. Therefore, they are integral in rendering transgender voice and communication training (TVCT), as part of their scope of practice. Research has, however, identified a lack of confidence in SLPs to render this service due to a perceived lack of education, knowledge, and clinical exposure. To determine the perceptions, knowledge, and perceived competencies of South African SLPs regarding TVCT. A cross-sectional open online survey design using non-probability purposive and convenience sampling was used. Fully qualified, practicing South African SLPs were asked to volunteer to participate on social media platforms. Fifty-two valid data sets were recorded. Most participants agreed that TVCT falls within their scope of practice (n = 42, 84%), viewing it as their ethical responsibility (n = 40, 80%) as well as a necessity (n = 34, 68%). However, most participants reported feeling inadequately prepared to provide TVCT (n = 34, 68%) due to insufficient education and training in this field, with 23 participants (45.1%) reporting that they had not received any education or training on the topic. Participants generally held positive attitudes toward TVCT yet felt unprepared to render the service due to insufficient education, training, and exposure, revealing a crucial professional development need.
- Open Access
- 1 January 2024
- Published by AOSIS in South African Journal of Communication Disorders
- Vol. 71 (1) , 9-e9
Caregivers’ perspectives of early developmental tele-assessments in challenging circumstances
Background: Outbreaks, such as the COVID-19 pandemic in 2020, exacerbate barriers to accessing early childhood developmental care. Tele-assessment may serve as an innovative approach to developmental monitoring to overcome service delivery amidst challenging circumstances. It is vital to collect caregivers’ perspectives of this potential service delivery method to inform clinical decision making. Objectives: This study aimed to determine caregivers’ perspectives of interview-based early developmental tele-assessment in a South African context. Method: Thirty caregivers of children (aged birth – 36 months) completed a caregiver-report developmental assessment via a telecommunications platform, as well as an online questionnaire probing their perspectives on the tele-assessment. Results: Most participants (96.7%, n = 29 out of 30) rated their overall experience of the tele-assessment as positive; however, 53.8% (n = 14 out of 26 that answered the question) indicated that they would additionally still prefer in-person assessment. Conclusion: Tele-assessment appears to be a viable approach for caregivers to access developmental care during circumstances such as COVID-19. Contribution: This study provided valuable insight into a novel approach using interview-based early developmental tele-assessment and the perspectives of caregivers thereof.
- 1 January 2024
- Published by AOSIS in South African Journal of Communication Disorders
- Vol. 71 (1) , 9-e9
Open AccessCaregivers’ perspectives of early developmental tele-assessments in challenging circumstances
Background: Outbreaks, such as the COVID-19 pandemic in 2020, exacerbate barriers to accessing early childhood developmental care. Tele-assessment may serve as an innovative approach to developmental monitoring to overcome service delivery amidst challenging circumstances. It is vital to collect caregivers’ perspectives of this potential service delivery method to inform clinical decision making. Objectives: This study aimed to determine caregivers’ perspectives of interview-based early developmental tele-assessment in a South African context. Method: Thirty caregivers of children (aged birth – 36 months) completed a caregiver-report developmental assessment via a telecommunications platform, as well as an online questionnaire probing their perspectives on the tele-assessment. Results: Most participants (96.7%, n = 29 out of 30) rated their overall experience of the tele-assessment as positive; however, 53.8% (n = 14 out of 26 that answered the question) indicated that they would additionally still prefer in-person assessment. Conclusion: Tele-assessment appears to be a viable approach for caregivers to access developmental care during circumstances such as COVID-19. Contribution: This study provided valuable insight into a novel approach using interview-based early developmental tele-assessment and the perspectives of caregivers thereof.
- Open Access
- 22 December 2023
- Published by AOSIS in Curationis
- Vol. 47 (1) , 9-e9
Nurses’ practices in stroke-related dysphagia in low- and middle-income countries
Background: Nurses are often required to perform dysphagia screening prior to oral intake by people following stroke. Previous studies report limited knowledge of nurses in identifying symptoms of post-stroke dysphagia. Objective: To explore existing literature regarding nurses’ practices and knowledge in the identification and management of post-stroke oropharyngeal dysphagia (OPD) in low- and middle income countries (LMICs). Method: A scoping review was conducted according to the PRISMA-ScR guidelines. Studies were retrieved from PubMed, Scopus, EBSCOhost (CINAHL and Health source: Nursing and Academic edition), Web of Science Core collection, and Cochrane libraries. No time frame was applied, and all included studies were screened according to predefined eligibility criteria. Results: Eight studies were included from 1 792 initial hits. Studies described nursing practices in acute care pertaining to identification and management of stroke-related dysphagia in LMICs. Increased knowledge was reported in nurses who had greater clinical experience in managing patients with dysphagia. Needs for training relating to dysphagia management and opportunities for interprofessional collaboration with speech-language therapists (SLTs) were identified. Contextual barriers specific to LMICs impacting on optimal nursing management of dysphagia included heavy workloads, staff-shortages and time constraints. Conclusion and contribution: Eight studies described nurses’ practices and identified needs for the improvement of nurses’ dysphagia care in LMICs. This scoping review highlighted the urgency for further research in dysphagia management that provides creative, contextually relevant solutions for improved protocols and training of health care professionals. Findings may be valuable for the multidisciplinary team involved in post-stroke dysphagia care.
- 22 December 2023
- Published by AOSIS in Curationis
- Vol. 47 (1) , 9-e9
Open AccessNurses’ practices in stroke-related dysphagia in low- and middle-income countries
Background: Nurses are often required to perform dysphagia screening prior to oral intake by people following stroke. Previous studies report limited knowledge of nurses in identifying symptoms of post-stroke dysphagia. Objective: To explore existing literature regarding nurses’ practices and knowledge in the identification and management of post-stroke oropharyngeal dysphagia (OPD) in low- and middle income countries (LMICs). Method: A scoping review was conducted according to the PRISMA-ScR guidelines. Studies were retrieved from PubMed, Scopus, EBSCOhost (CINAHL and Health source: Nursing and Academic edition), Web of Science Core collection, and Cochrane libraries. No time frame was applied, and all included studies were screened according to predefined eligibility criteria. Results: Eight studies were included from 1 792 initial hits. Studies described nursing practices in acute care pertaining to identification and management of stroke-related dysphagia in LMICs. Increased knowledge was reported in nurses who had greater clinical experience in managing patients with dysphagia. Needs for training relating to dysphagia management and opportunities for interprofessional collaboration with speech-language therapists (SLTs) were identified. Contextual barriers specific to LMICs impacting on optimal nursing management of dysphagia included heavy workloads, staff-shortages and time constraints. Conclusion and contribution: Eight studies described nurses’ practices and identified needs for the improvement of nurses’ dysphagia care in LMICs. This scoping review highlighted the urgency for further research in dysphagia management that provides creative, contextually relevant solutions for improved protocols and training of health care professionals. Findings may be valuable for the multidisciplinary team involved in post-stroke dysphagia care.