Curriculum Learning Based Approaches for Noise Robust Speaker Recognition

Performance of speaker identification (SID) systems is known to degrade rapidly in the presence of mismatch such as noise and channel degradations. This study introduces a novel class of curriculum learning (CL) based algorithms for noise robust speaker recognition. We introduce CL-based approaches...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE/ACM transactions on audio, speech, and language processing speech, and language processing, 2018-01, Vol.26 (1), p.197-210
Hauptverfasser:	Ranjan, Shivesh, Hansen, John H. L.
Format:	Artikel
Sprache:	eng
Schlagworte:	Curriculum learning (CL) Estimation Noise measurement noise robust Noise robustness probabilistic linear discriminant (PLDA) Rats Signal to noise ratio speaker verification Speech Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!