2022
DOI: 10.1017/s0272263122000080
|View full text |Cite
|
Sign up to set email alerts
|

Automated assessment of second language comprehensibility: Review, training, validation, and generalization studies

Abstract: Whereas many scholars have emphasized the relative importance of comprehensibility as an ecologically valid goal for L2 speech training, testing, and development, eliciting listeners’ judgments is time-consuming. Following calls for research on more efficient L2 speech rating methods in applied linguistics, and growing attention toward using machine learning on spontaneous unscripted speech in speech engineering, the current study examined the possibility of establishing quick and reliable automated comprehens… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
4
1

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
2

Relationship

0
6

Authors

Journals

citations
Cited by 6 publications
(5 citation statements)
references
References 65 publications
0
4
1
Order By: Relevance
“…This result could be due to the EFL teachers' similar contextual conditions, such as physical and social concerning curriculum, teaching practices, and aids and teaching approaches, namely the communicative teaching approach. This result is not line with that by Saito et al (2022) concluded that a variety of nonlinguistic elements such as speaker, age, gender, and microphone may affect automated speech recognition.…”
Section: Discussioncontrasting
confidence: 99%
See 1 more Smart Citation
“…This result could be due to the EFL teachers' similar contextual conditions, such as physical and social concerning curriculum, teaching practices, and aids and teaching approaches, namely the communicative teaching approach. This result is not line with that by Saito et al (2022) concluded that a variety of nonlinguistic elements such as speaker, age, gender, and microphone may affect automated speech recognition.…”
Section: Discussioncontrasting
confidence: 99%
“…Troyan et al (2013) implemented a practice-based approach centered around three key practices: comprehensive use of the target language during instruction, questioning to develop and gauge student understanding, teaching grammar inductively in meaningful contexts and co-constructing understanding. Saito et al (2022) examined the possibility of establishing quick and reliable automated comprehensibility assessments in which they gathered many spectrograms to build an acoustic model for each speech class. The spectrogram transmitted a variety of nonlinguistic elements "such as speaker, age, gender, and microphone" (p. 8).…”
Section: Literature Reviewmentioning
confidence: 99%
“…It is believed that native speakers have a negative perception of fluency with longer pauses (longer than 250 ms), and this threshold can best distinguish pauses (de Jong and Bosker 2013). The commonly used threshold of 250 ms is also selected in accordance with previous empirical research (e.g., Bao 2023;Saito et al 2022;Suzuki and Kormos 2023). Second, the silence threshold was set to −20 dB, which is supposed to avoid noise interference and fit into the classroom setting (Saito et al 2022).…”
Section: Measures Of Fluencymentioning
confidence: 99%
“…The commonly used threshold of 250 ms is also selected in accordance with previous empirical research (e.g., Bao 2023;Saito et al 2022;Suzuki and Kormos 2023). Second, the silence threshold was set to −20 dB, which is supposed to avoid noise interference and fit into the classroom setting (Saito et al 2022). Third, manual re-checking was carried out after automatic identification of pauses and syllables.…”
Section: Measures Of Fluencymentioning
confidence: 99%
“…Therefore, this paper proposes a new way of assessing E-TPS by using Praat as a device, with human interpretation as a rater. Such a combination is expected to reorient the pedagogical goal in pronunciation teaching from the traditional focus on accent reduction, to investigating global measures of prosody and fluency, reliable automated comprehensibility assessments, and the effect of mobile-based aural comprehension lessons (Isaacs, 2018;Kallio et al, 2023;Saito et al, 2022;Woldetsadik et al, 2022).…”
Section: Introductionmentioning
confidence: 99%