Language recognition on unknown conditions: the LORIA-Inria-MULTISPEECH system for AP20-OLR Challenge - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Language recognition on unknown conditions: the LORIA-Inria-MULTISPEECH system for AP20-OLR Challenge

Résumé

We describe the LORIA-Inria-MULTISPEECH system submitted to the Oriental Language Recognition AP20-OLR Challenge. This system has been specifically designed to be robust to unknown conditions: channel mismatch (task 1) and noisy conditions (task 3). Three sets of studies have been carried out for elaborating the system: design of multilingual bottleneck features, selection of robust features by evaluating language recognition performance on an unobserved channel, and design of the final models with different loss functions which exploit channel diversity within the training set. Key factors for robustness to unknown conditions are data augmentation techniques, stochastic weight averaging, and regularization of TDNNs with domain robustness loss functions. The final system is the combination of four TDNNs using bottleneck features and one GMM using SDC-MFCC features. Within the AP20-OLR Challenge, it achieves the top performance for tasks 1 and 3 with a $C_{avg}$ of respectively 0.0239 and 0.0374. This validates the approach for generalization to unknown conditions.
Fichier principal
Vignette du fichier
OLR20_interspeech2021_publication.pdf (299.75 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03228823 , version 1 (18-05-2021)
hal-03228823 , version 2 (17-06-2021)

Identifiants

Citer

Raphaël Duroselle, Md Sahidullah, Denis Jouvet, Irina Illina. Language recognition on unknown conditions: the LORIA-Inria-MULTISPEECH system for AP20-OLR Challenge. INTERSPEECH 2021, Aug 2021, Brno, Czech Republic. ⟨10.21437/Interspeech.2021-276⟩. ⟨hal-03228823v2⟩
226 Consultations
206 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More