MétaCan
Menu
Back to cohort
Record W4413127540 · doi:10.18280/ts.420449

A Deep Image Recognition-Based Automatic Evaluation Method for English Speaking Interaction Behaviors Enhanced by Attention Mechanisms

2025· article· en· W4413127540 on OpenAlexvenueno aff
Hongli Feng

Bibliographic record

VenueTraitement du signal · 2025
Typearticle
Languageen
FieldComputer Science
TopicEducational Technology and Pedagogy
Canadian institutionsnot available
Fundersnot available
KeywordsImage (mathematics)Artificial intelligenceComputer scienceSpeech recognitionPattern recognition (psychology)Natural language processingComputer vision

Abstract

fetched live from OpenAlex

Against the backdrop of globalization and the rapid advancement of intelligent education, English speaking interaction ability has become a core competence in international communication.Traditional manual evaluation methods suffer from low efficiency and strong subjectivity, making them inadequate for large-scale, objective assessments.Therefore, research on automatic evaluation methods for English speaking interaction behaviors is of significant practical importance.Current studies often rely solely on audio features, overlooking critical visual cues such as facial expressions and body movements, which results in incomplete assessments.While some approaches attempt to incorporate visual information, traditional image recognition models struggle to capture key features in complex interactive scenarios and lack effective mechanisms for integrating multidimensional features.To address these challenges, this study proposes an automatic evaluation method for English speaking interaction behaviors by integrating attention mechanisms with deep image recognition.The core contributions of this research are twofold: (1) the development of an interaction behavior recognition model based on an optimized attention mechanism, which consists of a global feature branch for holistic image feature extraction, an improved window-based attention branch for focusing on local key regions, and an enhanced channel attention branch for reinforcing important feature channels; (2) the design of an automatic evaluation framework that utilizes the accurately extracted features from the recognition model in conjunction with established speaking interaction assessment criteria to perform comprehensive evaluations.The innovations of this study lie in: (a) the proposed multi-branch attention model that enables precise extraction of global, local, and channel-specific features, overcoming the limitations of traditional models in feature representation; and (b) the deep integration of visual recognition with evaluation logic, establishing a complete technical pipeline from feature extraction to final assessment.This method significantly enhances the objectivity and accuracy of evaluations and offers a novel solution for intelligent spoken English assessment in the education domain.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.752
Threshold uncertainty score0.626

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.030
GPT teacher head0.359
Teacher spread0.330 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueTraitement du signalSame topicEducational Technology and PedagogyFrench-language works237,207