Semantic Scholar Open Access 2018 607 sitasi

Attentive Statistics Pooling for Deep Speaker Embedding

K. Okabe Takafumi Koshinaka K. Shinoda

Lihat Sumber DOI

Abstrak

This paper proposes attentive statistics pooling for deep speaker embedding in text-independent speaker verification. In conventional speaker embedding, frame-level features are averaged over all the frames of a single utterance to form an utterance-level feature. Our method utilizes an attention mechanism to give different weights to different frames and generates not only weighted means but also weighted standard deviations. In this way, it can capture long-term variations in speaker characteristics more effectively. An evaluation on the NIST SRE 2012 and the VoxCeleb data sets shows that it reduces equal error rates (EERs) from the conventional method by 7.5% and 8.1%, respectively.

Topik & Kata Kunci

Computer Science Engineering

Penulis (3)

K. Okabe

Takafumi Koshinaka

K. Shinoda

Format Sitasi

APA MLA BibTeX

Okabe, K., Koshinaka, T., Shinoda, K. (2018). Attentive Statistics Pooling for Deep Speaker Embedding. https://doi.org/10.21437/Interspeech.2018-993

Akses Cepat

Lihat di Sumber doi.org/10.21437/Interspeech.2018-993

Informasi Jurnal

Tahun Terbit: 2018
Bahasa: en
Total Sitasi: 607×
Sumber Database: Semantic Scholar
DOI: 10.21437/Interspeech.2018-993
Akses: Open Access ✓