(1) Background: Speech synthesis has customarily focused on adult speech, but with the rapid development of speech-synthesis technology, it is now possible to create child voices with a limited amount of child-speech data. This scoping review summarises the evidence base related to developing synthesised speech for children. (2) Method: The included studies were those that were (1) published between 2006 and 2021 and (2) included child participants or voices of children aged between 2–16 years old. (3) Results: 58 studies were identified. They were discussed based on the languages used, the speech-synthesis systems and/or methods used, the speech data used, the intelligibility of the speech and the ages of the voices. Based on the reviewed studies, relative to adult-speech synthesis, developing child-speech synthesis is notably more challenging. Child speech often presents with acoustic variability and articulatory errors. To account for this, researchers have most often attempted to adapt adult-speech models, using a variety of different adaptation techniques. (4) Conclusions: Adapting adult speech has proven successful in child-speech synthesis. It appears that the resulting quality can be improved by training a large amount of pre-selected speech data, aided by a neural-network classifier, to better match the children’s speech. We encourage future research surrounding individualised synthetic speech for children with CCN, with special attention to children who make use of low-resource languages.

Communication partners are instrumental in the successful use and implementation of augmentative and alternative communication systems (AAC), especially in schools, but stakeholder views from low- and middle-income countries (LMICs) are not well represented in the literature. Focus group interviews with seven professionals and three caregivers from South Africa were conducted to understand their perceptions and experiences of AAC use and implementation. The results highlighted additional issues which practitioners in LMICs need to consider when implementing AAC in under-resourced schools for learners with special education needs. Although some challenges overlap with those experienced in high-income countries, such as support and training, high staff turnover and burnout, large caseloads and language and codeswitching differences, these challenges present differently in low-income contexts, requiring alternative solutions. High-income countries do not often need to consider the risk a high-tech AAC device places on the child and their family due to the risk of crime in low-income contexts, the device affordability, the device features and the range of accents available when introducing an AAC system. This exploratory study suggests that LMICs, like South Africa, could make great strides towards providing appropriate AAC technology for all if i) strategic partnerships between governmental and non-governmental groups were put in place, ii) appropriate communication, training and support systems were established, and iii) evidence-based core-language AAC systems were created.

It is well-known that children with expressive communication difficulties have the right to communicate, but they should also have the right to do so in whichever language they choose, with a voice that closely matches their age, gender, and dialect. This study aimed to develop naturalistic synthetic child speech, matching the vocal identity of three children with expressive communication difficulties, using Tacotron 2, for three under-resourced South African languages, namely South African English (SAE), Afrikaans, and isiXhosa. Due to the scarcity of child speech corpora, 2 hours of child speech data per child was collected from three 11- to 12-year-old children. Two adult models were used to "warm start" the child speech synthesis. To determine the naturalness of the synthetic voices, 124 listeners participated in a mean opinion score survey (Likert Score) and optionally gave qualitative feedback. Despite limited training data used in this study, we successfully developed a synthesized child voice of adequate quality in each language. This study highlights that with recent technological advancements, it is possible to develop synthetic child speech that matches the vocal identity of a child with expressive communication difficulties in different under-resourced languages.

Background: There is a global need for synthetic speech development in multiple languages and dialects, as many children who cannot communicate using their natural voice struggle to find synthetic voices on high‐technology devices that match their age, social and linguistic background.Aims: To document multiple stakeholders’ perspectives surrounding the quality, acceptability and utility of newly created synthetic speech in three under‐resourced South African languages, namely South African English, Afrikaans and isiXhosa.Methods & Procedures: A mixed methods research design was selected. After the creation of naturalistic synthetic child speech which matched the vocal identity of three children with expressive communication difficulties, those three children answered questions about the quality, acceptability and utility of the synthetic voices using a pictographic three‐point scale. A total of 11 adults who are known to the children participated in subjective quality assessments in the form of mean opinion scores, intelligibility tests and focus group discussions.Outcomes & Results: Despite the synthetic adult voices appearing more natural, stakeholders were accepting of all the synthetic voices. Although personalization of the voices is important, intelligibility is prioritized and standard dialects are often preferred. When communication partners have adequate training and are willing to model and support children in all environments, children with expressive communication difficulties thrive, but when augmentative and alternative communication (AAC) use is inconsistent, there is reduced vocabulary development and poor system transitioning, and AAC abandonment is greater.Conclusions & Implications: This research suggests that stakeholders from low‐ and middle‐income countries are interested in the development of synthetic voices in their home languages. Our research highlights that children would prefer to incorporate these voices on their high‐tech devices, and adults would prefer them for their children, learners and/or clients’ devices, rather than using British or US English voices.WHAT THIS PAPER ADDS: What is already known on this subject: Caregivers, service providers, peers and other communication partners play a substantial role in a child AAC user's early communicative success, and their acceptance of AAC ultimately influences the effectiveness of the intervention. When communication partners advocate and support the inclusion of specific speech‐generating devices, AAC applications, and suitable synthetic voices, children are more willing to consistently utilize the technology. What this paper adds to the existing knowledge: As literature focusing on stakeholder perspectives from low‐ and middle‐income countries is less common than research from high‐income countries, and often lacks input from multi‐perspective stakeholders, our study offers a unique perspective from South African children with expressive communication difficulties, caregivers of those children, their speech–language pathologists and teachers, about the quality, acceptability and utility of synthetic speech in under‐resourced languages. What are the potential or clinical implications of this work?: Our research highlights that stakeholders would prefer South African languages and dialects on South African speech‐generating devices, rather than relying on devices that only incorporate British or US English voices. The development of synthetic speech in under‐resourced languages has the potential to support marginalized AAC communities. Children with expressive communication difficulties would finally be able to participate in class and do so with a voice that matches their age, gender and social and linguistic background. This paper highlights the importance of providing a variety of synthetic voice options and emphasizes the significance of introducing novel voices for high‐tech AAC to children in a manner that respects and aligns with their linguistic and cultural backgrounds.