SLPQualitativeInternational journal of language & communication disorders2025

Do you like my voice? Stakeholder perspectives about the acceptability of synthetic child voices in three South African languages.

Camryn Claire Terblanche, Michelle Pascoe, Michal Harty

PMID 39797624

WHAT IT FOUND

Stakeholders in South Africa accepted synthetic child voices in English, Afrikaans, and isiXhosa, though they rated the English child voice as less natural and harder to understand.

They emphasized that children should choose their own voice to match their identity, and that partner support is critical for adoption.

Key findings

01All three children with expressive communication difficulties indicated they liked the synthetic child voices created for them.

02Adult participants rated the English child voice as the worst quality and least natural, while preferring the Afrikaans and isiXhosa child voices.

03Stakeholders identified lack of communication partner involvement as one of the biggest barriers to high-tech AAC use.

STILL TO COME

How it was doneWhat they foundWhat it means for SLPs

Read the rest of this summary

You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.

Already have one?

What it does not show

The sample size was very small (3 children, 11 adults), so findings cannot be generalized to all AAC stakeholders in South Africa. The word error rate for isiXhosa should be interpreted cautiously due to linguistic differences between African languages and English. Few current AAC devices are capable of loading synthetic African voices, limiting immediate practical application.

Declared interests

The authors declare no conflicts of interest. The study was funded by the National Research Foundation.

The easy way to misread this

Do not conclude that synthetic child voices are ineffective or poorly accepted. While adults rated them lower than adult voices for intelligibility, the children themselves liked the voices, and stakeholders accepted them, highlighting that personalization and identity match are more critical for adoption than technical perfection.

Read it on PubMed →