WR3 in figures: what we measure, on what sample, and what is missing
WAV Research publishes six verified figures. The main one: WR3 agrees 90.4% with a human review on who is speaking, measured on 141 moments of a real 2026 session. Here are all six, each with its sample, its date, the method behind it and what it does not prove.
What are the figures, and on what sample?
This is everything we state with numbers on the site. If a figure is not here, we do not use it.
| Figure | What it measures | Sample | Date | Method | Limits |
|---|---|---|---|---|---|
| 90.4% | Agreement between WR3 and a human review on who is speaking at each moment. | 141 moments (556 seconds, 14 voices) from one block of about two and a half hours. | 2026 | Second-by-second comparison against a reference made by a person watching the video; includes the human review of flagged moments. | One block only. It clears the 90% target by a single moment, and each moment moves the figure by about 0.7 points. |
| 11 of 120 seconds | Seconds in which a lapel microphone's wearer was the loudest voice on their own microphone. | One two-minute window from one participant; in another window it was 37 of 120. | 2026 | Second-by-second comparison of each voice's level on that microphone. | Two windows from one focus group. They show the room-audio problem; they are not an average. |
| 1 in 10 | Quoted people whose words a hand-built report could attribute to them. | One delivered report, built from a single microphone for the whole room. | 2026 | Review of the report: how many quoted people had an identified speaker. | One report, made without WR3. It shows the limit of a room microphone; it does not measure WR3. |
| 38 of 38 | Quotes attributed to the right person. | The 38 attributed quotes in one delivery of a year-long focus group program. | 2026 | Audit of the delivery: each attributed quote was compared with who said it in the recording. | One delivery. Not a general error rate. |
| 20+ years | Track record of WAV (We Are Vision), the company behind WAV Research. | The company's history. | As of 2026 | Company record. | Years of experiential marketing, not years of running studies with WR3. |
| 600+ projects | Experiential marketing projects delivered by WAV. | The company's project record. | As of 2026 | Company record. | Experiential marketing projects, not research studies. |
How was each figure measured?
The first four come from real 2026 focus group recordings and deliveries, compared with a reference made by people. The detail of each measurement, with its stages and corrections, is in how we measure WR3's figures. The last two are company records: WAV's track record in experiential marketing, which is where the team, the room and the production come from.
One rule keeps us honest: every figure travels with its sample in the same sentence. "90.4%" alone says nothing; "90.4% on 141 moments from one block" can be checked.
What do these figures not prove?
- They are not averages across many waves. The 90.4% comes from one block. We will repeat it in more sessions and publish the result, up or down.
- They do not measure the market. They are about the quality of the method, not about what consumers think.
- They do not yet measure the total time of a study. We have measured steps one at a time, not the full path from recording to delivery.
When are they updated?
After the November 2026 wave we will publish the new figures here: the time from recording to delivery and the minutes of human review per session, each with its sample and date. This page's update date changes whenever a figure changes.
To see how these figures show up in a deliverable, browse the sample report, built from a fictional study.