pith. sign in

arxiv: 1803.10963 · v2 · pith:3RBQ2ZP4new · submitted 2018-03-29 · 📡 eess.AS · cs.SD

Attentive Statistics Pooling for Deep Speaker Embedding

Koji Okabe , Takafumi Koshinaka , Koichi Shinoda This is my paper
classification 📡 eess.AS cs.SD
keywords speakerembeddingattentiveconventionaldeepdifferentframesmethod
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. DeepASA: An Object-Oriented Multi-Purpose Network for Auditory Scene Analysis

    eess.AS 2025-09 unverdicted novelty 7.0

    DeepASA unifies source separation, dereverberation, SED, classification, and DoAE via object-oriented processing, chain-of-inference, and temporal coherence matching, reporting SOTA on ASA2, MC-FUSS, and STARSS23.

  2. Variational Encoder--Multi-Decoder (VE-MD) for Privacy-by-functional-design (Group) Emotion Recognition

    cs.CV 2026-04 unverdicted novelty 6.0

    VE-MD uses a shared variational latent space jointly optimized for group affect classification and structural body/face decoding, delivering SOTA results on GAF-3.0 and VGAF while never producing individual emotion or...

  3. A Systematic Evaluation of Co-folding Model Representations for Small-Molecule Learning

    q-bio.BM 2026-02 unverdicted novelty 6.0

    Boltz2 co-folding representations match or exceed existing models on ADMET benchmarks, accelerate generative modeling, and improve sample efficiency in ligand optimization while being complementary to 3D, bioassay, an...

  4. Acoustic Scene Classification Using Fusion of Attentive Convolutional Neural Networks for DCASE2019 Challenge

    eess.AS 2019-07 unverdicted novelty 2.0

    Fusion of VGG-like 2D CNN, Light-CNN, and x-vector 1D CNN with self-attention pooling on 256-dim log Mel-spectrograms, trained on 4-fold splits and combined with multiple fusion strategies for DCASE2019 Task 1.