---
title: Open-Source Speaker Diarization for Overlapping Dialogue
seo_title: Open-Source Speaker Diarization for Overlapping Dialogue
description: Evaluate open-source speaker diarization on interruptions and overlapping
  dialogue. Compare turn boundaries, speaker attribution, and transcript error metrics.
author: Model Workflow Lab Editorial
author_type: Organization
date: '2026-11-11'
lastmod: '2026-11-11'
topic: Speech Transcription and Diarization
faq:
- q: Does cpCER measure overlapping speech directly?
  a: It measures speaker-grouped text error after matching labels. Use overlap-marked
    reference intervals to assess simultaneous speech.
- q: Should I include short acknowledgments?
  a: Include them if they matter to the deliverable. Report the scoring policy for
    short turns.
- q: Is a joint model a good starting point?
  a: Yes when the output needs readable words, timestamps, and attribution together.
    Assess dedicated diarization for a timeline-only workflow.
category: library
copyright: Copyright 2026 ModelWorkflowLab.com; subject to stated permissions and
  exceptions.
---
# Open-Source Speaker Diarization for Overlapping Dialogue

## Which diarization model should you test on overlapping dialogue?

Include MOSS-Transcribe-Diarize 0.9B if the deliverable is a transcript with timestamps and speaker labels. The Apache-2.0 release combines speech recognition and diarization. If a project requires an explicit timeline of simultaneous speakers, verify that its output format and scoring policy cover that use case. [Release repository](https://github.com/OpenMOSS/MOSS-Transcribe-Diarize)

<figure>
<img src="/assets/images/speaker-diarization-overlapping-dialogue.svg" alt="Mark overlap then Compare speaker turns then Review missed voices" width="1140" height="200" loading="lazy" />
<figcaption>Proposed evaluation workflow. Mark overlap. Compare speaker turns. Review missed voices.</figcaption>
</figure>

## Read the public dialogue demo at turn level

The official page presents a scene where two speakers discuss buying a watermelon. The transcript alternates anonymous labels across short turns and includes start and end times. The demo illustrates how quickly attribution can change during a conversation. It provides a place to inspect the output structure. [Official demonstrations](https://www.moss.cn/en/models/moss-transcribe-diarize)

For a proposed panel-recording audit, choose passages containing interruptions, brief acknowledgments, and actual simultaneous speech. An interruption followed by silence and two speakers talking at once need different annotations. We would keep both in the review set because a single total can hide which kind caused the error.

| Review question | Suitable evidence |
|---|---|
| Is speech assigned to the right speaker? | Reference speaker timeline and diarization error rate |
| Are spoken words retained under the right label? | cpCER and error examples |
| Does the output represent overlapping intervals? | Inspection against marked overlap regions |
| Does a voice get split into several identities? | Speaker mapping across distant segments |

## Compare diarization with speaker-attributed recognition

Diarization error rate measures time-based errors such as missed speech, false alarms, and speaker confusion under a stated scoring setup. The scoring collar and treatment of overlap affect the result. The published AISHELL-4 numbers for MOSS-Transcribe-Diarize 0.9B are **14.84% CER and 15.83% cpCER**. Those figures describe text and speaker-grouped text errors. An overlap-specific DER claim requires another evaluation. [Technical report](https://arxiv.org/abs/2601.01554) · [Benchmark table](https://github.com/OpenMOSS/MOSS-Transcribe-Diarize)

Have two reviewers mark the difficult segments and resolve disagreements before scoring. Test a dedicated diarization route alongside joint recognition if a multi-speaker activity timeline is mandatory. Keep that comparison tied to the same recording and scoring settings.

Use the official [checkpoint](https://huggingface.co/OpenMOSS-Team/MOSS-Transcribe-Diarize) and consult the [serving cookbook](https://github.com/sgl-project/sglang-omni/blob/main/docs/cookbook/moss_transcribe_diarize.md) for output handling. For adjacent decisions see [diarization selection](/best-open-source-speaker-diarization-model/), [SOTA attribution evidence](/sota-open-source-speaker-diarization/), and [meeting action review](/speech-to-text-meeting-action-items/).

## English SEO keywords

open-source speaker diarization, overlapping dialogue, DER, cpCER, MOSS-Transcribe-Diarize.