Multi-task Metric Learning for Text-independent Speaker Verification
In this work, we introduce metric learning (ML) to enhance the deep embedding learning for text-independent speaker verification (SV). Specifically, the deep speaker embedding network is trained with conventional cross entropy loss and auxiliary pair-based ML loss function. For the auxiliary ML task...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | In this work, we introduce metric learning (ML) to enhance the deep embedding
learning for text-independent speaker verification (SV). Specifically, the deep
speaker embedding network is trained with conventional cross entropy loss and
auxiliary pair-based ML loss function. For the auxiliary ML task, training
samples of a mini-batch are first arranged into pairs, then positive and
negative pairs are selected and weighted through their own and relative
similarities, and finally the auxiliary ML loss is calculated by the similarity
of the selected pairs. To evaluate the proposed method, we conduct experiments
on the Speaker in the Wild (SITW) dataset. The results demonstrate the
effectiveness of the proposed method. |
---|---|
DOI: | 10.48550/arxiv.2010.10919 |