> ## Documentation Index
> Fetch the complete documentation index at: https://docs.voicemark.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# EER results

> Clone test harness results — 0.0% Equal Error Rate for both conditions.

VoiceMark's speaker verification was tested against two adversarial conditions using the ECAPA-TDNN pipeline (`spkrec-ecapa-voxceleb`, 192-dim) with cosine similarity.

## Methodology

* **Genuine pairs**: Three recordings of the target speaker (enrolled + two verify samples)
* **Impostor condition A — human**: 12 recordings from different speakers from the same audio corpus
* **Impostor condition B — pre-existing AI**: 13 recordings from pre-existing synthetic/cloned voices (non-IVC)
* **Metric**: Equal Error Rate (EER) — the threshold where FAR (false accept rate) equals FRR (false reject rate)

## Results

| Condition | EER |
| - | - |
| Human impostors | **0.0%** |
| Pre-existing AI clones | **0.0%** |

Genuine speaker scores and impostor scores show no overlap at the operating threshold, with a wide separation margin between the two distributions.

## Configuration

* **Similarity metric**: Cosine similarity on speaker embeddings
* **Threshold**: Tuned per deployment environment
* **Liveness**: f0 variation analysis (not applied in this test run)

## Upcoming conditions

The following conditions are planned for future test runs:

* **XTTS-v2 open-source clone** (local, \$0 cost) — IVC using the target speaker's enrollment audio
* **Hesitation signature analysis** — comparing disfluency/pause patterns in real speech vs TTS output


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.