A Triplet Ranking-Based Neural Network for Speaker Diarization and Linking

Gaël Le Lan (1) , Delphine Charlet (1) , Anthony Larcher (2) , Sylvain Meignier (2)

1 Orange Labs [Lannion]
2 LIUM - Laboratoire d'Informatique de l'Université du Mans

This paper investigates a novel neural scoring method, based on conventional i-vectors, to perform speaker diarization and linking of large collections of recordings. Using triplet loss for training, the network projects i-vectors in a space that better separates speakers in terms of cosine similarity. Experiments are run on two French TV collections built from REPERE [1] and ETAPE [2] campaigns corpora, the system being trained on French Radio data. Results indicate that the proposed approach outperforms conventional cosine and Probabilistic Linear Discriminant Analysis scoring methods on both within-and cross-recording diarization tasks, with a Diarization Error Rate reduction of 14% in average.

Mots clés: speaker diarization; neural network; triplet loss

Domaines: Intelligence artificielle [cs.AI]

Gaël Le Lan, Delphine Charlet, Anthony Larcher, Sylvain Meignier. A Triplet Ranking-Based Neural Network for Speaker Diarization and Linking. Interspeech 2017, Aug 2017, Stockholm, Sweden. ⟨10.21437/Interspeech.2017-270⟩. ⟨hal-01818401⟩