# voxmap-studio: An open-source speaker diarization annotation tool with built-in cost instrumentation

arXiv: https://arxiv.org/abs/2606.26842 · HTML: https://mlsanity.com/paper/2606.26842/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Speaker recognition and diarization, one of 11 directions in Speech and audio language models.
- Builds on 2 of its 5 references that are in the map.
- First posted on arXiv 25 Jun 2026.

## Placed in

- Speech and audio language models / [Speaker recognition and diarization](https://mlsanity.com/speech/speaker-recognition-and-diarization/)

## Builds on (most cited first, 2 of 2)

- [Powerset multi-class cross entropy loss for neural speaker diarization](https://mlsanity.com/paper/2310.13025/) (2023)
- [Fast and Robust On-Device Speaker Diarization: Relative Minimum Cluster Size for Stride-Accelerated Pipelines](https://mlsanity.com/paper/2606.08505/) (2026)

## Abstract (arXiv)

Labeling speaker diarization data is costly, yet annotation tools rarely measure that cost. We present voxmap-studio, an open-source, React-based diarization annotation tool integrated with the pyannote-based diarization ecosystem. Its canvas is initialized by a fast stride-accelerated diarization engine so that the annotator corrects a hypothesis rather than drawing every speaker turn by hand, and the tool records annotation cost - typed edit-operation counts and time - as a first-class output, enabling quantitative comparison of how much different forms of assistance actually help. Export is gated on per-segment human confirmation and guarded by injected "phantom" attention checks, which prevent unverified automatic output from being released as ground truth. In a preliminary study on nine AMI audio files, unassisted manual annotation was the costliest and least accurate, and automatic initialization shifted the work from creating turns to correcting them; highlighting uncertain segments gave the lowest cost in our small sample. The tool and its instrumentation are open source.