Datasets › EVI
EVI
The EVI dataset is a challenging, multilingual spoken-dialogue dataset with 5,506 dialogues in English, Polish, and French. The dataset can be used to develop and benchmark conversational systems for user authentication tasks, i.e. speaker enrolment (E), speaker verification (V), speaker identification (I).
The dataset contains the audio data, machine transcriptions, and target identity for each dialogue, and the knowledge-base with personal information (postcode, name, and date of birth) for each identity. The dataset can be used with both text-independent biometric or knowledge-based authentication (KBA) tasks.
Benchmarks archive 2025-07-28
All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Speaker Identification | EVI en-GB | Fuzzy Retrieval Top-1 (%) 67.77 | EVI: Multilingual Spoken Dialogue Tasks and Dataset for... | PolyAI-LDN/evi-paper | 1 | Compare |
| Speaker Identification | EVI fr-FR | Fuzzy Retrieval Top-1 (%) 80.83 | EVI: Multilingual Spoken Dialogue Tasks and Dataset for... | PolyAI-LDN/evi-paper | 1 | Compare |
| Speaker Identification | EVI pl-PL | Fuzzy Retrieval Top-1 (%) 95.13 | EVI: Multilingual Spoken Dialogue Tasks and Dataset for... | PolyAI-LDN/evi-paper | 1 | Compare |
Papers archive 2025-07-28
1 shown of 1 paper with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 1. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and Identification | 1 | 3 | 28 Apr 2022 | not harvested |
Dataset loaders archive 2025-07-28
1 loader as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
Languages archive 2025-07-28
Variants archive 2025-07-28
- EVI
- EVI en-GB
- EVI pl-PL
- EVI fr-FR
4 variant names, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections