Rainbow passage with ASR transcription and segmental error rate (SER)

Product or Programme · All products and programmes
Evidence · 2 claims (2 for) · 1 study (1 causal), q2 · 1 of 1 report an effect size · 2 claims rest on one study

Description

A pronunciation diagnostic assessment that uses the Rainbow passage, automatic speech-to-text transcription, and segmental error-rate scoring to identify learners' pronunciation errors.

Components

• Rainbow passage with ASR transcription and segmental error rate (SER) as a pronunciation diagnostic instrument: A diagnostic assessment instrument combining the Rainbow passage (adapted from Fairbanks, 1960, and validated for Korean pronunciation assessment by Yang, 2020) with ASR speech-to-text transcription. The study "combined Penkhae's (2020) focus on problematic sounds with Yang's (2020) simplified rubric", narrowing the focus from whole words to commonly mispronounced sounds. Recordings are transcribed by Google Cloud speech to text, errors are categorized against a list of errors common to L1 Korean speakers, and a segmental error rate is computed over the passage's 131 syllables, enabling error diagnosis without subjective differences between raters. (Dillon et al. (2023))

Claims

• ASR transcription serves as a diagnostic tool identifying individual learners' pronunciation errors, with function words most commonly mispronounced [+W]
• An online word error rate checker correlates strongly with the study's segmental error rate measure, offering a quick pronunciation accuracy score [+W]

Related Products and Programmes

-

Key Sources

• Dillon, Thomas, & Wells, Donald. (2023). Effects of pronunciation training using automatic speech recognition on pronunciation accuracy of Korean English language learners. English Teaching, 78(1), 3-23. https://doi.org/10.15858/engtea.78.1.202303.3

Page metadata

Field	Value
type	product
id	rainbow-passage-with-asr-transcription-and-segmental-error-rate-ser
title	Rainbow passage with ASR transcription and segmental error rate (SER)
description	A pronunciation diagnostic assessment that uses the Rainbow passage, automatic speech-to-text transcription, and segmental error-rate scoring to identify learners' pronunciation errors.
status	review
moved_from	element/rainbow-passage-ser-diagnostic-instrument
product_kind	assessment
generated	by process:sweep-kinds on 2026-10-10
trust	unverified — no one has confirmed this page's content
sources	1 — dillon-2023

Frontmatter is the page's machine-readable record — see the Schema & Guide.