# Human Evaluation on Hindi spoken dialogue (test)

Source: [Human Evaluation on Hindi spoken dialogue (test)](<https://www.sota2.com/research/sota/human-evaluation-on-hindi-spoken-dialogue-test>)

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

Data updated: 2026-04-28T07:50:28.942Z

Human evaluation of spoken dialogue systems using the Hindi spoken dialogue test set, assessing quality across dimensions like Naturalness, Clarity, and Human Preference.

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 | Human Evaluation |
| Dataset (including any stated split) | Hindi spoken dialogue (test) |
| Metric | Naturalness |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Naturalness](<https://www.sota2.com/research/sota/human-evaluation-on-hindi-spoken-dialogue-test.md?metric=Naturalness>): Higher is better; unit: SCALAR.

- [Clarity](<https://www.sota2.com/research/sota/human-evaluation-on-hindi-spoken-dialogue-test.md?metric=Clarity>): Higher is better; unit: SCALAR.

- [Human Preference](<https://www.sota2.com/research/sota/human-evaluation-on-hindi-spoken-dialogue-test.md?metric=Human%20Preference>): Higher is better; unit: PERCENT.

- [Model Preference](<https://www.sota2.com/research/sota/human-evaluation-on-hindi-spoken-dialogue-test.md?metric=Model%20Preference>): Higher is better; unit: PERCENT.

- [Tie Preference](<https://www.sota2.com/research/sota/human-evaluation-on-hindi-spoken-dialogue-test.md?metric=Tie%20Preference>): Higher is better; unit: PERCENT.

- [Human-like Interaction](<https://www.sota2.com/research/sota/human-evaluation-on-hindi-spoken-dialogue-test.md?metric=Human-like%20Interaction>): Higher is better; unit: PERCENT.

- [Appropriateness](<https://www.sota2.com/research/sota/human-evaluation-on-hindi-spoken-dialogue-test.md?metric=Appropriateness>): Higher is better; unit: PERCENT.

- [Completion](<https://www.sota2.com/research/sota/human-evaluation-on-hindi-spoken-dialogue-test.md?metric=Completion>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Naturalness | Result date | Report paper |
| --- | --- | --- | --- |
| Human | 4.55 | Not recorded | 69f03eea55a3c32af89f9eed |
| Human-1 | 4.1 | Not recorded | 69f03eea55a3c32af89f9eed |

### Human

Naturalness: 4.55. Result ID: 69f0664b47f34ce924d60950.

[Reporting paper](<https://www.sota2.com/research/paper/69f03eea55a3c32af89f9eed.md>)

Recorded evaluation configuration: {"Entity":"Human"}. This record does not assert independent reproduction.

### Human-1

Naturalness: 4.1. Result ID: 69f0664b47f34ce924d6094f.

[Reporting paper](<https://www.sota2.com/research/paper/69f03eea55a3c32af89f9eed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03eea55a3c32af89f9eed.md>)

Recorded evaluation configuration: {"Entity":"Model"}. This record does not assert independent reproduction.

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