Deep neural network-based speaker embeddings for end-to-end speaker verification

Citations Over TimeTop 1% of 2016 papers

Abstract

In this study, we investigate an end-to-end text-independent speaker verification system. The architecture consists of a deep neural network that takes a variable length speech segment and maps it to a speaker embedding. The objective function separates same-speaker and different-speaker pairs, and is reused during verification. Similar systems have recently shown promise for text-dependent verification, but we believe that this is unexplored for the text-independent task. We show that given a large number of training speakers, the proposed system outperforms an i-vector baseline in equal error-rate (EER) and at low miss rates. Relative to the baseline, the end-to-end system reduces EER by 13% average and 29% pooled across test conditions. The fused system achieves a reduction of 32% average and 38% pooled.

Related Papers

• → Never-ending learning system for on-line speaker diarization(2007)28 cited
• → Unsupervised text independent speaker classification(2002)15 cited
• → Text-independent speaker verification using speaker clustering and support vector machines(2003)6 cited
• → Speaker Recognition and Diarization(2010)3 cited
• → Fixed-Phrase Speaker Verification(2011)