A Study of Teaching Quality Improvement in English Listening Teaching in the Context of Speech Recognition Technology
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
At present, most English learners spend much less time listening to English than reading it.Most of the language knowledge is acquired through visual channels rather than auditory channels, thus the language knowledge does not form corresponding auditory images in the mind, so the phenomenon of reading but not understanding occurs.Aiming at this kind of problem, this paper tries to explore the role of speech recognition in improving the quality of English teaching by combining it with this technology.The article first recognizes English spoken speech features based on Mel's frequency cepstrum feature parameters and deep belief network, then expands the number of speech features from both time and frequency by means of distortion and masking, and designs the encoder part by combining 2D convolutional neural networks and GRUs, and finally models the local and temporal information in the speech features to realize the recognition of English speech.And thus establish a new model of English listening teaching.As verified by the dataset, the method in this paper can accurately recognize speech features of different emotions, and the recognition effect is better than other models of the same type.In addition, an equivalence study between the proposed teaching model and the traditional teaching model was conducted with 70 foreign students in a university.It was found that the mean value of the total scores of the candidates in the group of the teaching model proposed in this paper was 0.26 points higher than the mean value of the total scores of the candidates in the traditional group, among which, the mean value of the listening scores of the candidates in the group of the teaching model proposed in this paper was 0.1 points higher than the mean value of the listening scores of the candidates in the traditional group.
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.
Full frame distilled prediction
Teacher imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.015 | 0.007 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it