Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-1593
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-16T18:13:02.782894Z
status: published
lens: g_space
sector: health
headline: Novel Approaches to Language Assessment Part 1: Artificial Intelligence-Automated Scoring of a Sentence Recall Task for School-Age Children
dek: Purpose Artificial intelligence (AI) technologies have the potential to enhance the delivery of speech-language pathology services. One area of practice that could benefit from AI is automated screenings for developmental language disorder (DLD) in early elementary students. This report presents the elements and processes involved in evaluating an AI-based automated scoring system using archival recordings. Method A total of 947 audio samples of children completing the Redmond Sentence Recall (RSR) task, represe…
gain_title: An AI scoring pipeline for the Redmond Sentence Recall task matched the reference standard more closely than human-scored protocols and showed sensitivity of .768 to .873 for identifying DLD.
problem_title: (none)
trace_subject: (none)
gain_reading: An AI scoring pipeline for the Redmond Sentence Recall task matched the reference standard more closely than human-scored protocols and showed sensitivity of .768 to .873 for identifying DLD.
gain_evidence: it converged more closely with the reference standard than human-scored protocols | AI technologies have become powerful enough to automate the scoring of recordings of children's sentence recall with similar accuracy levels as human evaluators
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers built AutoRSR, a system that uses speech recognition, natural language processing, and machine learning to transcribe children's recordings of a sentence recall task, count errors, score accuracy, and issue pass/fail screening decisions for developmental language disorder. They tested it on 947 archival audio samples from children with and without the disorder.

The results suggest that scoring of this screening task could be automated at accuracy comparable to human evaluators, which may ease demands on speech-language pathology services. The report describes an evaluation using archival recordings, and the abstract states that next steps are still to be discussed, so real-world use is not yet shown.
limitation: The system showed some mismatches with human evaluators and tended to produce lower scores, and the reference-standard comparison covered only a 130-child subset of the 947 samples.
tag: Evidence-backed gain
key_points: The study used 947 archival audio samples of children completing the Redmond Sentence Recall task, covering cases with and without DLD. | A subset of 130 children had Core Language scores from the Clinical Evaluation of Language Fundamentals-Fourth Edition, used as the reference standard. | With Whisper speech recognition, AutoRSR reached sensitivity of .768 and specificity of .784. | With Reverb speech recognition, sensitivity rose to .873 while specificity fell to .730, showing a trade-off between the two models.
rundown: The AutoRSR pipeline automates four tasks: transcribing recordings, tracking the number of errors children produce, scoring production accuracy by RSR criteria, and generating pass/fail decisions based on age-referenced expectations. It was built on automated speech recognition, natural language processing, and machine learning models.

Two speech recognition models were compared to examine trade-offs. Reverb gave higher sensitivity, meaning more children with DLD were flagged, while Whisper gave slightly higher specificity.

The system did not match human evaluators exactly. It showed some mismatches with human scorers and tended to produce lower scores, but it still converged more closely with the reference standard than human-scored protocols did.
sources:
- peer_reviewed | Language, Speech, and Hearing Services in Schools | https://doi.org/10.1044/2026_lshss-25-00268 | 2026-10-09
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

d6c3a3fd06145b45dfb1aac677a51e7a8a531553909607fda7b10f1cd80fde44

previous

0000000000000000000000000000000000000000000000000000000000000000