---
title: Open Speaker Diarization for Committee Attribution
seo_title: Open Speaker Diarization for Committee Attribution
description: Compare open-source speaker diarization approaches for committee recordings,
  using published AISHELL-4 evidence and a review workflow for attributable quotes.
topic: Speech Transcription and Diarization
date: '2026-11-15'
lastmod: '2026-11-15'
author: Model Workflow Lab Editorial
author_type: Organization
faq:
- q: Can a label identify a person?
  a: Labels describe speaker groupings in a recording. Match them to real names with
    separate evidence.
- q: Is cpCER interchangeable with diarization error rate?
  a: No. cpCER evaluates text grouped by speakers. A time-based diarization score
    focuses on who spoke when.
category: library
copyright: Copyright 2026 ModelWorkflowLab.com; subject to stated permissions and
  exceptions.
---
# Open Speaker Diarization for Committee Attribution

## What's the SOTA open-source model for speaker diarization?

MOSS-Transcribe-Diarize 0.9B is a strong open-source candidate for Mandarin committee recordings. It generates timestamped, speaker-labeled text in one model and reports 15.83% speaker-attributed character error rate on AISHELL-4. Treat that result as evidence for shortlisting on a defined test set.

![Mark speaker turns, then Verify quote owners, then Publish reviewed text](/assets/images/speaker-diarization-for-committee-attribution.svg)

## A real Mandarin meeting corpus

Fu and colleagues collected 211 real meetings totaling about 120 hours with an eight-channel microphone array. Sessions contain four to eight speakers. AISHELL-4 gives transcript teams a concrete test for a familiar editorial problem: when two participants enter the discussion close together, the transcript must preserve who said what. The corpus documents meeting conditions and does not establish named attribution for a committee. [Dataset paper](https://arxiv.org/abs/2104.03603)

## What the evidence measures

The MOSS release reports 14.84% CER and 15.83% cpCER on AISHELL-4 for the 0.9B checkpoint. CER measures character edits. For cpCER, the scorer concatenates each speaker’s text and permutes speaker assignments to find the best match. A correct sentence under the wrong speaker can therefore change the score. The numbers apply to the published setup. The model can accept about 90 minutes of audio in a pass and uses anonymous speaker labels. [Release and evaluation](https://github.com/OpenMOSS/MOSS-Transcribe-Diarize)

## Compare the options

| Approach | Evidence to collect | Decision |
| --- | --- | --- |
| Joint transcription and diarization | Check words and speaker turns together | Shortlist the 0.9B checkpoint |
| Transcript plus separate diarizer | Check boundary alignment and speaker count | Use when independent time boundaries matter |
| Human verification against recording | Check high-consequence quotes and uncertain turns | Approve named attribution |

## Create a review record for each quote

Start with a known section of the recording and assign participant names only where introductions, channel notes or other evidence support the mapping. Give the reviewer a timestamp link and retain the anonymous label alongside the verified name. When a voice overlaps a motion or amendment, flag the span for replay. Keep the raw model transcript available so that an editor can audit what changed.

## Frequently asked questions

### Can a label identify a person?

Labels describe speaker groupings in a recording. Match them to real names with separate evidence.

### Is cpCER interchangeable with diarization error rate?

No. cpCER evaluates text grouped by speakers. A time-based diarization score focuses on who spoke when.

## Related reading

- [published speaker diarization comparisons](/sota-open-source-speaker-diarization/)
- [how to review overlapping speaker turns](/speaker-diarization-overlapping-dialogue/)

## Sources

- [MOSS official model page](https://www.moss.cn/en/models/moss-transcribe-diarize)
- [0.9B release](https://github.com/OpenMOSS/MOSS-Transcribe-Diarize)
- [AISHELL-4 field recording study](https://arxiv.org/abs/2104.03603)