I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences
2 UEF - University of Eastern Finland = Itä-Suomen Yliopisto = Östra Finlands universitet
3 NEC Corporation
4 Academia Sinica
5 LIUM - Laboratoire d'Informatique de l'Université du Mans
6 NUS - National University of Singapore
7 LIA - Laboratoire Informatique d'Avignon
8 NTU - Nanyang Technological University [Singapour]
9 MATEIS - Matériaux, ingénierie et science [Villeurbanne]
10 CAAS - Chinese Academy of Agricultural Sciences
11 CRSS - Center for Robust Speech Systems
12 Eurecom [Sophia Antipolis]
13 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
14 JD AI Research and Platform
- Fonction : Auteur
- PersonId : 20105
- IdHAL : anthony-larcher
- ORCID : 0000-0003-4398-0224
- IdRef : 139544569
- Fonction : Auteur
- PersonId : 743667
- IdHAL : jose-patino
- ORCID : 0000-0001-7193-0721
- IdRef : 241999308
- Fonction : Auteur
- PersonId : 737397
- IdHAL : sahid
- Fonction : Auteur
- PersonId : 172421
- IdHAL : jean-francois-bonastre
- ORCID : 0000-0001-7741-3346
- IdRef : 079112978
- Fonction : Auteur
- PersonId : 1199117
- ORCID : 0000-0003-2883-0324
- IdRef : 279030118
- Fonction : Auteur
- PersonId : 938450
- ORCID : 0000-0002-8459-1041
- IdRef : 168937859
Résumé
The I4U consortium was established to facilitate a joint entry to NIST speaker recognition evaluations (SRE). The latest edition of such joint submission was in SRE 2018, in which the I4U submission was among the best-performing systems. SRE'18 also marks the 10-year anniversary of I4U consortium into NIST SRE series of evaluation. The primary objective of the current paper is to summarize the results and lessons learned based on the twelve subsystems and their fusion submitted to SRE'18. It is also our intention to present a shared view on the advancements, progresses, and major paradigm shifts that we have witnessed as an SRE participant in the past decade from SRE'08 to SRE'18. In this regard, we have seen, among others , a paradigm shift from supervector representation to deep speaker embedding, and a switch of research challenge from channel compensation to domain adaptation.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|---|
| Licence |