TristouNet: Triplet loss for speaker turn embedding
TL
TL;DR
Experiments on short speech turn comparison and speaker change detection show that TristouNet brings significant improvements over the current state-of-the-art techniques for both tasks.
Abstract
TristouNet is a neural network architecture based on Long Short-Term Memory recurrent networks, meant to project speech sequences into a fixed-dimensional euclidean space. Thanks to the triplet loss paradigm used for training, the resulting sequence embeddings can be compared directly with the euclidean distance, for speaker comparison purposes. Experiments on short (between 500ms and 5s) speech turn comparison and speaker change detection show that TristouNet brings significant improvements over the current state-of-the-art techniques for both tasks.
References26 items
1
Front-End Factor Analysis For Speaker Verification
2
A Discriminative Feature Learning Approach for Deep Face Recognition
3
Speaker-aware training of LSTM-RNNS for acoustic modelling
4
FaceNet: A unified embedding for face recognition and clustering
5