Identity
- Type
- open community
- Country label
- France / Canada
- HQ country
- France
- Founding country
- not in the notes
- Parent
- not in the notes
- Parent country
- not in the notes
- Country basis
- the research notes
Where this comes from
Convention D1: a dual label, HQ first, when the HQ, founding or parent country differ.
Models by Class
Models
ModelClassOpennessParametersReleased
MetricGAN+music and audio8 Apr 2021SepFormermusic and audio25 Oct 2020ECAPA-TDNN (SpeechBrain)speaker–x-vector speaker recognition (VoxCeleb)speaker–VoxLingua107 language ID (ECAPA)audio classification–Emotion recognition wav2vec2 (IEMOCAP)audio classification–VAD CRDNN (LibriParty)audio classification–Links
OrganisationSpeechBrain communityopen community, France / Canada
SpeechBrain communityopen community, France / CanadaModelsMetricGAN+SpeechBrain community, music and audioSepFormerSpeechBrain community, music and audioECAPA-TDNN (SpeechBrain)SpeechBrain community, speakerx-vector speaker recognition (VoxCeleb)SpeechBrain community, speaker+3 more
MetricGAN+SpeechBrain community, music and audioSepFormerSpeechBrain community, music and audioECAPA-TDNN (SpeechBrain)SpeechBrain community, speakerx-vector speaker recognition (VoxCeleb)SpeechBrain community, speaker+3 moreUse Casesnone recorded
Who Runs Itnone recorded
Models 7
ECAPA-TDNN (SpeechBrain)SpeechBrain community, speakerDeveloperEmotion recognition wav2vec2 (IEMOCAP)SpeechBrain community, audio classificationDeveloperMetricGAN+SpeechBrain community, music and audioDeveloperSepFormerSpeechBrain community, music and audioDeveloperVAD CRDNN (LibriParty)SpeechBrain community, audio classificationDeveloperVoxLingua107 language ID (ECAPA)SpeechBrain community, audio classificationDeveloperx-vector speaker recognition (VoxCeleb)SpeechBrain community, speakerDeveloperScores
| Benchmark | Model | Score | Who ran it | Setting |
|---|---|---|---|---|
| VoxCeleb1 (cleaned) | ECAPA-TDNN (SpeechBrain) | 0.8 EER % | vendor-reported | cleaned VoxCeleb1, speaker verification |
Where this comes from
Every recorded score of this organisation's models, with who ran it. Scores from different settings are not directly comparable.
Sources
- Top 7 Speaker Diarization APIs and Models in 2026 - pyannoteAI Speaker Intelligence and Diarization pyannote.ai https://www.pyannote.ai/blog/top-7-speaker-diarization-apis-and-models-in-2026
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "SpeechBrain Community", https://aurion.semai.id/organisations/speechbrain/, records of October 2026.