Details
| Original language | English |
|---|---|
| Pages (from-to) | 1-12 |
| Number of pages | 12 |
| Journal | Folia phoniatrica et logopaedica |
| Volume | 75 |
| Issue number | 1 |
| Early online date | 7 Oct 2022 |
| Publication status | Published - 24 Jan 2023 |
Abstract
Background: Language sample analysis (LSA) is invaluable to describe and understand child language use and development for clinical purposes and research. Digital tools supporting LSA are available, but many of the LSA steps have not been automated. Nevertheless, programs that include automatic speech recognition (ASR), the first step of LSA, have already reached mainstream applicability. Summary: To better understand the complexity, challenges, and future needs of automatic LSA from a technological perspective, including the tasks of transcribing, annotating, and analysing natural child language samples, this article takes on a multidisciplinary view. Requirements of a fully automated LSA process are characterized, features of existing LSA software tools compared, and prior work from the disciplines of information science and computational linguistics reviewed. Key Messages: Existing tools vary in their extent of automation provided across the process of LSA. Advances in machine learning for speech recognition and processing have potential to facilitate LSA, but the specifics of child speech and language as well as the lack of child data complicate software design. A transdisciplinary approach is recommended as feasible to support future software development for LSA.
Keywords
- Assessment, Automatic speech recognition, Child language, Language sample analysis
ASJC Scopus subject areas
- Arts and Humanities(all)
- Language and Linguistics
- Social Sciences(all)
- Linguistics and Language
- Health Professions(all)
- Speech and Hearing
- Nursing(all)
- LPN and LVN
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Folia phoniatrica et logopaedica, Vol. 75, No. 1, 24.01.2023, p. 1-12.
Research output: Contribution to journal › Review article › Research › peer review
}
TY - JOUR
T1 - Multidisciplinary Perspectives on Automatic Analysis of Children's Language Samples
T2 - Where Do We Go from Here?
AU - Lüdtke, Ulrike
AU - Bornman, Juan
AU - De Wet, Febe
AU - Heid, Ulrich
AU - Ostermann, Jörn
AU - Rumberg, Lars
AU - Van Der Linde, Jeannie
AU - Ehlert, Hanna
PY - 2023/1/24
Y1 - 2023/1/24
N2 - Background: Language sample analysis (LSA) is invaluable to describe and understand child language use and development for clinical purposes and research. Digital tools supporting LSA are available, but many of the LSA steps have not been automated. Nevertheless, programs that include automatic speech recognition (ASR), the first step of LSA, have already reached mainstream applicability. Summary: To better understand the complexity, challenges, and future needs of automatic LSA from a technological perspective, including the tasks of transcribing, annotating, and analysing natural child language samples, this article takes on a multidisciplinary view. Requirements of a fully automated LSA process are characterized, features of existing LSA software tools compared, and prior work from the disciplines of information science and computational linguistics reviewed. Key Messages: Existing tools vary in their extent of automation provided across the process of LSA. Advances in machine learning for speech recognition and processing have potential to facilitate LSA, but the specifics of child speech and language as well as the lack of child data complicate software design. A transdisciplinary approach is recommended as feasible to support future software development for LSA.
AB - Background: Language sample analysis (LSA) is invaluable to describe and understand child language use and development for clinical purposes and research. Digital tools supporting LSA are available, but many of the LSA steps have not been automated. Nevertheless, programs that include automatic speech recognition (ASR), the first step of LSA, have already reached mainstream applicability. Summary: To better understand the complexity, challenges, and future needs of automatic LSA from a technological perspective, including the tasks of transcribing, annotating, and analysing natural child language samples, this article takes on a multidisciplinary view. Requirements of a fully automated LSA process are characterized, features of existing LSA software tools compared, and prior work from the disciplines of information science and computational linguistics reviewed. Key Messages: Existing tools vary in their extent of automation provided across the process of LSA. Advances in machine learning for speech recognition and processing have potential to facilitate LSA, but the specifics of child speech and language as well as the lack of child data complicate software design. A transdisciplinary approach is recommended as feasible to support future software development for LSA.
KW - Assessment
KW - Automatic speech recognition
KW - Child language
KW - Language sample analysis
UR - http://www.scopus.com/inward/record.url?scp=85146484499&partnerID=8YFLogxK
U2 - 10.1159/000527427
DO - 10.1159/000527427
M3 - Review article
C2 - 36209730
AN - SCOPUS:85146484499
VL - 75
SP - 1
EP - 12
JO - Folia phoniatrica et logopaedica
JF - Folia phoniatrica et logopaedica
SN - 1021-7762
IS - 1
ER -