Speech Recognition Software Contributes to Reading Development for Young Learners of English

Reeder, Kenneth; Shapiro, Jerry; Wakefield, Jane; D'Silva, Reg

doi:10.4018/ijcallt.2015070104

Cited by 9 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Interventions were classed as having a high (Reeder et al, 2015) or medium risk of bias (Schechter et al, 2015;Trainin et al, 2016).…”

Section: Technology-enhanced Literacymentioning

confidence: 99%

“…Four interventions used software to improve reading fluency and vocabulary (Schechter et al, 2015;Trainin et al, 2016;Reeder et al, 2015;Leacox & Jackson, 2014). In spite of the lack of information about cost and a possible bias issue (for example one intervention was funded by Pearson Education), these interventions did show gains with effect sizes ranging from small to large (see Table 11).…”

Section: Summary Of Evidencementioning

confidence: 99%

See 1 more Smart Citation

A systematic review of language and literacy interventions in children and adolescents with English as an additional language (EAL)

Oxley

Cat

2019

The Language Learning Journal

View full text Add to dashboard Cite

Objective: A synthesis of evidence discussing the effectiveness of language and literacy interventions in children with English as an additional language. Our key research questions were: 1) What intervention studies have been published since 2014 addressing the language and literacy development of children with English as an additional language? 2) What is the impact of those interventions? We sought to update a 2015 systematic review evaluating language and literacy outcomes for EAL children (Murphy & Unthiah, 2015) with current intervention studies and to see which of those interventions could be adapted for classrooms in the UK. Methods: Four databases were searched; PsychInfo, British Education Index, Education Resources Information Center and Web of Science. Only peer reviewed journal articles published between 2014 and 2017 and written in English were included. The population tested were children of school age with English as an Additional Language who were classed as typically developing. All interventions had language or literacy as an outcome. Data was extracted using a standardised form and quality was assessed through a risk of bias analysis. From this screening process, 26 studies were eligible for inclusion in the current review. Key Findings:  Explicit vocabulary instruction and targeted oral language practise yield language gains for EAL learners, with a tendency for larger intervention gains in learners with the lowest initial pre-test scores.  Shared reading interventions show positive effects when combined with the preteaching of vocabulary, embedded definitions into the text, or post-reading reinforcement activities.  Voice recognition software appears promising, as demonstrated in three interventions with small to medium effects on reading fluency and comprehension.  There is a lack of interventions taking place in the UK.  There is a lack of interventions for adolescents, especially those in upper secondary school (ages 14-18).  More interventions targeting continued professional development for teachers are recommended. Conclusions: Children with English as an additional language can benefit from targeted interventions. Suggestions are made as to how the most beneficial interventions could be replicated in the UK. Limitations: Limitations include a variability in terms of the rigour of intervention methodologies, leading to a high risk of bias and inconsistent effect sizes for several studies in this report. A proportion of successful interventions used the child's first language to aid learning. Such interventions might not be replicable in the UK, where classrooms typically feature children from a very large number of different home languages.

show abstract

“…Interventions were classed as having a high (Reeder et al, 2015) or medium risk of bias (Schechter et al, 2015;Trainin et al, 2016).…”

Section: Technology-enhanced Literacymentioning

confidence: 99%

Section: Summary Of Evidencementioning

confidence: 99%

A systematic review of language and literacy interventions in children and adolescents with English as an additional language (EAL)

Oxley

Cat

2019

The Language Learning Journal

View full text Add to dashboard Cite

show abstract

“…Most of the research that has been conducted so far on applying ASR in the context of reading skills acquisition [12,31,36] addressed reading skills in English [25,26,32]. Many of the studies addressed reading assessment at a global level [35,5] or were aimed at monitoring children while they read aloud whole passages and at providing some form of support when they encounter difficulties [9].…”

Section: Research Backgroundmentioning

confidence: 99%

“…The idea that automatic speech recognition (ASR) technology can be employed to support children learning to read has been around for quite a while [26,36,32]. Various research systems and commercial products have been proposed [20,27,11] that can monitor children while reading and indicate when they encounter difficulties.…”

Section: Introductionmentioning

confidence: 99%

An ASR-Based Tutor for Learning to Read: How to Optimize Feedback to First Graders

Bai¹,

Tejedor-Garcı́a²,

Hubers³

et al. 2021

Speech and Computer

View full text Add to dashboard Cite

The interest in employing automatic speech recognition (ASR) in applications for reading practice has been growing in recent years. In a previous study, we presented an ASR-based Dutch reading tutor application that was developed to provide instantaneous feedback to first-graders learning to read. We saw that ASR has potential at this stage of the reading process, as the results suggested that pupils made progress in reading accuracy and fluency by using the software. In the current study, we used children's speech from an existing corpus (JAS-MIN) to develop two new ASR systems, and compared the results to those of the previous study. We analyze correct/incorrect classification of the ASR systems using human transcripts at word level, by means of evaluation measures such as Cohen's Kappa, Matthews Correlation Coefficient (MCC), precision, recall and F-measures. We observe improvements for the newly developed ASR systems regarding the agreement with human-based judgment and correct rejection (CR). The accuracy of the ASR systems varies for different reading tasks and word types. Our results suggest that, in the current configuration, it is difficult to classify isolated words. We discuss these results, possible ways to improve our systems and avenues for future research.

show abstract

“…Systems have been built using measures related to pronunciation, fluency, and reading accuracy, words per minute count, and have achieved high correlations with human judgments of English proficiency, e.g. [6,7,8,9]. Sabu et al have employed Automated Speech Recognition (ASR) and prosody modeling for evaluating the reading levels of children [9].…”

Section: Related Workmentioning

confidence: 99%

A Dataset for Measuring Reading Levels In India At Scale

Agarwal

Gupchup

Baghel

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

1One out of four children in India are leaving grade eight without basic reading skills. Measuring the reading levels in a vast country like India poses significant hurdles. Recent advances in machine learning opens up the possibility of automating this task. However, the datasets of children's speech are not only rare but are primarily in English. To solve this assessment problem and advance deep learning research in regional Indian languages, we present the ASER dataset of children in the age group of 6-14. The dataset consists of 5,301 subjects generating 81,330 labeled audio clips in Hindi, Marathi and English. These labels represent expert opinions on the child's ability to read at a specified level. Using this dataset, we built a simple ASR-based classifier. Early results indicate that we can achieve a prediction accuracy of 86% for the English language. Considering the ASER survey spans half a million subjects, this dataset can grow to those scales.

show abstract

Speech Recognition Software Contributes to Reading Development for Young Learners of English

Cited by 9 publications

References 21 publications

A systematic review of language and literacy interventions in children and adolescents with English as an additional language (EAL)

A systematic review of language and literacy interventions in children and adolescents with English as an additional language (EAL)

An ASR-Based Tutor for Learning to Read: How to Optimize Feedback to First Graders

A Dataset for Measuring Reading Levels In India At Scale

Contact Info

Product

Resources

About