Accent Classification using Machine Learningin English Language
Bibliographic record
Abstract
AbstractThe increasing reliance on voice-activated technology in daily life has highlighted the need forASR systems that can accurately understand a range of English accents. Current systems of-ten struggle with diverse accents, impacting the inclusivity and effectiveness of speech-basedinteractions. This thesis explores accent classification in the English language, focusing onfive major accents: American, British, Indian, Australian, and Canadian. Using supervisedmachine learning methods, including CNN, SVM, and RF models, this study investigates theeffectiveness of these models in classifying different accents.The research uses the Mozilla Common Voice dataset, which offers a diverse collection oflabeled audio samples. Through experimental evaluation, the performance of CNN, SVM,and RF models is assessed in accurately classifying the specified accents. The findings in-dicate that while CNNs achieve an accuracy of 70%, traditional machine learning methodsoutperform CNNs, with SVMs reaching an accuracy of 83% and RFs achieving 79%. Notably,SVMs excelled in differentiating US and Canadian accents with precision rates of 90% and88%, respectively.Overall, this work contributes to the development of more inclusive and adaptable speechrecognition systems, benefiting applications in customer service, virtual assistance, and othervoice-based technologies. Additionally, the thesis reflects on the challenges encountered dur-ing the study, including model over-fitting and difficulties in distinguishing subtle accentvariations, and discusses potential avenues for future research to enhance accent classifica-tion methodologies.
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 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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 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 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
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".