Attentive Statistics Pooling For Deep Speaker Embedding

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.

Stats

• citations328
• S2 citations—
• github stars0
• HF likes0
• heat score18.88
• arxiv keyokabe2018attentive

Related papers

• Exploring A Unified Attention-based Pooling Framework For Speaker Verification (2018)6.77
• Deep Speaker Embedding Learning With Multi-level Pooling For Text-independent Speaker Verification (2019)0.00
• Attention Mechanism In Speaker Recognition: What Does It Learn In Deep Speaker Embedding? (2018)8.60
• Double Multi-head Attention For Speaker Verification (2020)8.09
• Deep Segment Attentive Embedding For Duration Robust Speaker Verification (2018)2.26
• Recursive Attentive Pooling For Extracting Speaker Embeddings From Multi-speaker Recordings (2024)2.26
• Phonetic-attention Scoring For Deep Speaker Features In Speaker Verification (2018)2.26
• Socov: Semi-orthogonal Parametric Pooling Of Covariance Matrix For Speaker Recognition (2025)0.00