MeetEval alignment visualization tool

This tool visualizes word sequence alignments to facilitate spotting of errors in conversational ASR transcription

Examples

Poster example

Example screenshot

The example displayed on the poster presented at ICASSP 2024 Show&Tell.

LibriCSS tcpWER

Example screenshot

A high-overlap (OV40) example from the LibriCSS dataset.

LibriCSS CSS tcORC-WER

Example screenshot

A high-overlap (OV40) example from the LibriCSS dataset, separated with a Continuous Speech Separation (CSS) pipeline and evaluated with the speaker agnostic tcORC-WER.

DiPCo tcpWER

Example screenshot

Error analysis on a DiPCo session processed by Paderborn University's submission to the 7th CHiME challenge.

Side-by-side System Comparison

Example screenshot

Two synchronized visualizations to compare different systems. Here: NTT's and Paderborn University's submissions to the 7th CHiME challenge (DiPCo dataset).

Side-by-side tcpWER vs. cpWER

Example screenshot

Comparison of the tcp alignment (with time constraint) with the cp alignment (without time constraint).

JupyterLite Notebook

JupyterLite screenshot

The JupyterLite notebook that generates the visualization in the browser. Run it with you own data, no installation required!

Session Browser

Session browser screenshot

Browse results across different sessions.

Poster

Poster mini

The poster presented at the ICASSP 2024 Show & Tell Demo session as PDF