Towards the phonetic basis of spoken second language assessment: temporal features as indicators of perceived proficiency level

Kallio, Heini; Simko, Juraj; Huhta, Ari; Karhila, Reima; Vainio, Martti; Lindroos, Erik; Hildén, Raili; Kurimo, Mikko

doi:10.30660/afinla.73137

Cited by 7 publications

(11 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So, this method can serve as a part of an automated assessment system. As a part of integration process, we will assess to what extent the prominence based evaluation provides complementary information to the existing prosody evaluation measures such as disfluencies, pauses, and articulation rate [20].…”

Section: Discussionmentioning

confidence: 99%

Prominence-based Evaluation of L2 Prosody

Kallio¹,

Suni²,

Virkkunen³

et al. 2018

Interspeech 2018

Self Cite

View full text Add to dashboard Cite

Prosody in terms of word and sentence stress is one of the most difficult features for many second language (L2) speakers to learn and it can be hypothesized that assessing the learner's prosodic abilities could provide a good measure for assessing the learners' spoken language skills in general. Automatic assessment is, however, dependent on reliable automatic analyses of prosodic features for comparing the productions between native (L1) and L2 speech. Here we investigate, whether estimated prosodic prominence levels of syllables can be used to predict the prosodic competence of Finnish learners of Swedish. Syllable level prominence was estimated for 99 L2 and 25 native Swedish utterances using continuous wavelet transform analysis with combinations of f0, energy, and duration features. The L2 utterances were assessed by four expert raters using the revised CEFR scale for prosodic features. Correlations of prominence estimates for L2 utterances with estimates for L1 utterances and linguistic stress patterns were used as a measure of prosodic proficiency of the L2 speakers. The results show that these estimates correlate significantly with the assessments of expert raters. Overall, the results provide strong support for the use of the wavelet-based prominence estimation techniques in automatic assessment of L2 proficiency.

show abstract

Section: Discussionmentioning

confidence: 99%

Prominence-based Evaluation of L2 Prosody

Kallio¹,

Suni²,

Virkkunen³

et al. 2018

Interspeech 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…Fluency is a frequently used term in language pedagogy and testing, but it has several definitions: in its broad sense, L2 fluency is often synonymous with general L2 proficiency, while the narrow definition, also examined as utterance fluency [1], refers to the fluidity or temporal features of speech [2]. Researchers have found temporal fluency measures to be strong predictors of human assessments of fluency [2,3,4,5,6,7] as well as oral proficiency [8,9,10,11], and similar features have also been incorporated in automatic assessment systems [12].…”

Section: Introductionmentioning

confidence: 99%

Creaky voice and utterance fluency measures in predicting fluency and oral proficiency of spontaneous L2 Finnish

Kallio¹,

Suviranta²,

Kuronen³

et al. 2022

Speech Prosody 2022

Self Cite

View full text Add to dashboard Cite

While utterance fluency measures are often studied in relation to perceived L2 fluency and proficiency, the effect of creaky voice remains ignored. However, creaky voice is frequent in a number of languages, including Finnish, where it serves as a cue for phrase-boundaries and turn-taking. In this study we investigate the roles of creaky voice and utterance fluency measures in predicting fluency and proficiency ratings of spontaneous L2 Finnish (F2) speech. In so doing, 16 expert raters participated in assessing narrative spontaneous speech samples from 160 learners of Finnish. The effect of creaky voice and utterance fluency measures on proficiency and fluency ratings was studied using linear regression models. The results indicate that creaky voice can contribute to both oral proficiency and fluency alongside utterance fluency measures. Furthermore, average duration of composite breaks -a measure combining breakdown and repair phenomena -proved to be the most significant predictor of fluency. Based on these findings we recommend further investigation of the effect of creaky voice to the assessment of L2 speech as well as reconsideration of the utterance fluency measures used in predicting L2 fluency or proficiency.

show abstract

“…We expect both methods to be applicable for distinguishing speakers with different proficiency levels, following the findings of Kallio et al (2017 , 2020 ). Based on the previous studies discussed above, we expect the temporal measures to be good predictors of prosodic proficiency regardless of the speaker’s L1.…”

Section: Introductionmentioning

confidence: 81%

“…Prosodic features have, however, also been found to explain a substantial amount of the variance in general oral proficiency ratings ( Kang et al, 2010 ). In particular, temporal features related to speech fluency have proven to be strong predictors of prosodic competence ( Cheng, 2011 ; Hönig et al, 2010 ; Kallio et al, 2017 ; Kang & Johnson, 2018 ), which is why we start by reviewing studies related to the temporal fluency of L2 speech. Although fluency research has commonly focused on measuring temporal features, arguments have been raised that fluency involves both temporal and intonational phenomena ( Kang et al, 2010 ; Kormos & Dénes, 2004 ).…”

Section: Introductionmentioning

confidence: 99%

“…The diversity of these results can be attributed to different conceptualizations and operationalizations of fluency and its measures as well as to the different types of analyzed data. There are, for example, some inconsistencies in defining pauses: depending on the study and speech material, the pause threshold ranges from 50 ms to as long as 3 s ( Bosker et al, 2013 ; Derwing et al, 2004 ; Kallio et al, 2017 ; Kormos & Dénes, 2004 ; Préfontaine et al, 2016 ), which can result in characterizing similar data with different parameter values. Some acoustic measures, in turn, are confounds: for example, both speech rate and mean duration of pause are related to the duration of pauses in the speech signal and are therefore interrelated, which can affect the interpretation of the results.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fluency-related Temporal Features and Syllable Prominence as Prosodic Proficiency Predictors for Learners of English with Different Language Backgrounds

2021

Self Cite

View full text Add to dashboard Cite

Prosodic features are important in achieving intelligibility, comprehensibility, and fluency in a second or foreign language (L2). However, research on the assessment of prosody as part of oral proficiency remains scarce. Moreover, the acoustic analysis of L2 prosody has often focused on fluency-related temporal measures, neglecting language-dependent stress features that can be quantified in terms of syllable prominence. Introducing the evaluation of prominence-related measures can be of use in developing both teaching and assessment of L2 speaking skills. In this study we compare temporal measures and syllable prominence estimates as predictors of prosodic proficiency in non-native speakers of English with respect to the speaker’s native language (L1). The predictive power of temporal and prominence measures was evaluated for utterance-sized samples produced by language learners from four different L1 backgrounds: Czech, Slovak, Polish, and Hungarian. Firstly, the speech samples were assessed using the revised Common European Framework of Reference scale for prosodic features. The assessed speech samples were then analyzed to derive articulation rate and three fluency measures. Syllable-level prominence was estimated by a continuous wavelet transform analysis using combinations of F0, energy, and syllable duration. The results show that the temporal measures serve as reliable predictors of prosodic proficiency in the L2, with prominence measures providing a small but significant improvement to prosodic proficiency predictions. The predictive power of the individual measures varies both quantitatively and qualitatively depending on the L1 of the speaker. We conclude that the possible effects of the speaker’s L1 on the production of L2 prosody in terms of temporal features as well as syllable prominence deserve more attention in applied research and developing teaching and assessment methods for spoken L2.

show abstract

Towards the phonetic basis of spoken second language assessment: temporal features as indicators of perceived proficiency level

Cited by 7 publications

References 0 publications

Prominence-based Evaluation of L2 Prosody

Prominence-based Evaluation of L2 Prosody

Creaky voice and utterance fluency measures in predicting fluency and oral proficiency of spontaneous L2 Finnish

Fluency-related Temporal Features and Syllable Prominence as Prosodic Proficiency Predictors for Learners of English with Different Language Backgrounds

Contact Info

Product

Resources

About