# Answering Machine Detection on Production (val)

Source: [Answering Machine Detection on Production (val)](<https://www.sota2.com/research/sota/answering-machine-detection-on-production-val>)

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

Data updated: 2026-04-14T07:22:12.181Z

Evaluation of model performance on the validation split of the Production dataset for Answering Machine Detection, measured using Accuracy, Time-to-Decision, and False Positives.

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 | Answering Machine Detection |
| Dataset (including any stated split) | Production (val) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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/answering-machine-detection-on-production-val.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Time-to-Decision (s)](<https://www.sota2.com/research/sota/answering-machine-detection-on-production-val.md?metric=Time-to-Decision%20(s)>): Lower is better; unit: TIME.

- [False Positive Rate](<https://www.sota2.com/research/sota/answering-machine-detection-on-production-val.md?metric=False%20Positive%20Rate>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Transcription keywords | 97.6 | Not recorded | 69ddca047d0172140ec79925 |
| VAD-15 (temporal VAD features) | 96.1 | Not recorded | 69ddca047d0172140ec79925 |
| Industry AMD (silence heuristics) | 70 | Not recorded | 69ddca047d0172140ec79925 |
| Beep detection (DESA-2) | 50.7 | Not recorded | 69ddca047d0172140ec79925 |

### Transcription keywords

Accuracy: 97.6. Result ID: 69ddeb0a47f34ce924c4f3c8.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca047d0172140ec79925.md>)

Recorded evaluation configuration: {"GPU Required":"Yes"}. This record does not assert independent reproduction.

### VAD-15 (temporal VAD features)

Accuracy: 96.1. Result ID: 69ddeb0a47f34ce924c4f3c5.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca047d0172140ec79925.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddca047d0172140ec79925.md>)

Recorded evaluation configuration: {"GPU Required":"No"}. This record does not assert independent reproduction.

### Industry AMD (silence heuristics)

Accuracy: 70. Result ID: 69ddeb0a47f34ce924c4f3c7.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca047d0172140ec79925.md>)

Recorded evaluation configuration: {"GPU Required":"No"}. This record does not assert independent reproduction.

### Beep detection (DESA-2)

Accuracy: 50.7. Result ID: 69ddeb0a47f34ce924c4f3c6.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca047d0172140ec79925.md>)

Recorded evaluation configuration: {"GPU Required":"No"}. This record does not assert independent reproduction.

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