A Situational Analysis of Current Speech-Synthesis Systems for Child Voices: A Scoping Review of Qualitative and Quantitative Evidence
| dc.contributor.author | Terblanche, Camryn | |
| dc.contributor.author | Harty, Michal | |
| dc.contributor.author | Pascoe, Michelle | |
| dc.contributor.author | Tucker, Benjamin V | |
| dc.date.accessioned | 2022-08-31T20:44:44Z | |
| dc.date.available | 2022-08-31T20:44:44Z | |
| dc.date.issued | 2022-06-01 | |
| dc.date.updated | 2022-06-09T13:40:45Z | |
| dc.description.abstract | 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) <i>Method:</i> 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) <i>Results:</i> 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) <i>Conclusions:</i> 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. | en_US |
| dc.identifier | doi: 10.3390/app12115623 | |
| dc.identifier.apacitation | Terblanche, C., Harty, M., Pascoe, M., & Tucker, B. V. (2022). A Situational Analysis of Current Speech-Synthesis Systems for Child Voices: A Scoping Review of Qualitative and Quantitative Evidence. <i>Applied Sciences</i>, 12(11), 5623. http://hdl.handle.net/11427/36792 | en_ZA |
| dc.identifier.chicagocitation | Terblanche, Camryn, Michal Harty, Michelle Pascoe, and Benjamin V Tucker "A Situational Analysis of Current Speech-Synthesis Systems for Child Voices: A Scoping Review of Qualitative and Quantitative Evidence." <i>Applied Sciences</i> 12, 11. (2022): 5623. http://hdl.handle.net/11427/36792 | en_ZA |
| dc.identifier.citation | Terblanche, C., Harty, M., Pascoe, M. & Tucker, B.V. 2022. A Situational Analysis of Current Speech-Synthesis Systems for Child Voices: A Scoping Review of Qualitative and Quantitative Evidence. <i>Applied Sciences.</i> 12(11):5623. http://hdl.handle.net/11427/36792 | en_ZA |
| dc.identifier.ris | TY - Journal Article AU - Terblanche, Camryn AU - Harty, Michal AU - Pascoe, Michelle AU - Tucker, Benjamin V AB - 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) <i>Method:</i> 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) <i>Results:</i> 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) <i>Conclusions:</i> 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. DA - 2022-06-01 DB - OpenUCT DP - University of Cape Town IS - 11 J1 - Applied Sciences LK - https://open.uct.ac.za PY - 2022 T1 - A Situational Analysis of Current Speech-Synthesis Systems for Child Voices: A Scoping Review of Qualitative and Quantitative Evidence TI - A Situational Analysis of Current Speech-Synthesis Systems for Child Voices: A Scoping Review of Qualitative and Quantitative Evidence UR - http://hdl.handle.net/11427/36792 ER - | en_ZA |
| dc.identifier.uri | http://hdl.handle.net/11427/36792 | |
| dc.identifier.vancouvercitation | Terblanche C, Harty M, Pascoe M, Tucker BV. A Situational Analysis of Current Speech-Synthesis Systems for Child Voices: A Scoping Review of Qualitative and Quantitative Evidence. Applied Sciences. 2022;12(11):5623. http://hdl.handle.net/11427/36792. | en_ZA |
| dc.language.iso | en | en_US |
| dc.publisher.department | Department of Pathology | en_US |
| dc.publisher.faculty | Faculty of Health Sciences | en_US |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | en_US |
| dc.source | Applied Sciences | en_US |
| dc.source.journalissue | 11 | en_US |
| dc.source.journalvolume | 12 | en_US |
| dc.source.pagination | 5623 | en_US |
| dc.title | A Situational Analysis of Current Speech-Synthesis Systems for Child Voices: A Scoping Review of Qualitative and Quantitative Evidence | en_US |
| dc.type | Journal Article | en_US |