Work

TristouNet: Triplet loss for speaker turn embedding

Year: 2017
Type: conference-paper
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.
Author: Herve Bredin
Language: English
Open Access status: green
OpenAlex ID: W2519781924
FWCI: 11.13
Cites: 19
Cited by: 210
Related to: 10