# 4-way Dialect Classification on Gan Chinese dialect corpus (nonduplicated speakers)

Source: [4-way Dialect Classification on Gan Chinese dialect corpus (nonduplicated speakers)](<https://www.sota2.com/research/sota/4-way-dialect-classification-on-gan-chinese-dialect-corpus-nonduplicated-speakers>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-18T07:35:33.707Z

Evaluation of a model's ability to perform 4-way dialect classification using the nonduplicated speakers subset of the Gan Chinese dialect corpus, measured by Accuracy.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | 4-way dialect classification |
| Dataset (including any stated split) | Gan Chinese dialect corpus (nonduplicated speakers) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/4-way-dialect-classification-on-gan-chinese-dialect-corpus-nonduplicated-speakers.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SVM\_unigram | 58.65 | Not recorded | 6a337bb7206542251d7c5147 |
| Speech-Driven End-to-End Language Discrimination (predicted attention word) | 42.29 | Not recorded | 6a337bb7206542251d7c5147 |
| Speech-Driven End-to-End Language Discrimination (predicted word) | 36.56 | Not recorded | 6a337bb7206542251d7c5147 |

### SVM\_unigram

Accuracy: 58.65. Result ID: 6a339fbefbc373592c309065.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bb7206542251d7c5147.md>)

Recorded evaluation configuration: {"Model type":"Text-driven models","Feature":"unigram"}. This record does not assert independent reproduction.

### Speech-Driven End-to-End Language Discrimination (predicted attention word)

Accuracy: 42.29. Result ID: 6a339fbefbc373592c309067.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bb7206542251d7c5147.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bb7206542251d7c5147.md>)

Recorded evaluation configuration: {"Model type":"Text-driven models","Input text":"predicted attention word"}. This record does not assert independent reproduction.

### Speech-Driven End-to-End Language Discrimination (predicted word)

Accuracy: 36.56. Result ID: 6a339fbefbc373592c309066.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bb7206542251d7c5147.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bb7206542251d7c5147.md>)

Recorded evaluation configuration: {"Model type":"Text-driven models","Input text":"predicted word"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.