# Parameter-Free Attentive Scoring for Speaker Verification

arXiv: https://arxiv.org/abs/2203.05642 · HTML: https://mlsanity.com/paper/2203.05642/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 43 references that are in the map.
- First posted on arXiv 10 Mar 2022.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [Generalized End-to-End Loss for Speaker Verification](https://mlsanity.com/paper/1710.10467/) (2017)
- [Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling](https://mlsanity.com/paper/1902.08295/) (2019)
- [End-to-End Text-Dependent Speaker Verification](https://mlsanity.com/paper/1509.08062/) (2015)
- [CN-CELEB: a challenging Chinese speaker recognition dataset](https://mlsanity.com/paper/1911.01799/) (2019)
- [Self-attention encoding and pooling for speaker recognition](https://mlsanity.com/paper/2008.01077/) (2020)
- [Attention-Based Models for Text-Dependent Speaker Verification](https://mlsanity.com/paper/1710.10470/) (2017)
- [Probabilistic embeddings for speaker diarization](https://mlsanity.com/paper/2004.04096/) (2020)
- [Dr-Vectors: Decision Residual Networks and an Improved Loss for Speaker Recognition](https://mlsanity.com/paper/2104.01989/) (2021)
- [S-vectors and TESA: Speaker Embeddings and a Speaker Authenticator Based on Transformer Encoder](https://mlsanity.com/paper/2008.04659/) (2020)
- [Multi-View Self-Attention Based Transformer for Speaker Recognition](https://mlsanity.com/paper/2110.05036/) (2021)
- [Version Control of Speaker Recognition Systems](https://mlsanity.com/paper/2007.12069/) (2020)
- [Graph Attention Networks for Speaker Verification](https://mlsanity.com/paper/2010.11543/) (2020)
- [Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speech](https://mlsanity.com/paper/2202.12163/) (2022)
- [Text-Independent Speaker Verification with Dual Attention Network](https://mlsanity.com/paper/2009.05485/) (2020)
- [Improving Speaker Identification for Shared Devices by Adapting Embeddings to Speaker Subsets](https://mlsanity.com/paper/2109.02576/) (2021)

## Built on by (most cited first, 2 of 2)

- [Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations](https://mlsanity.com/paper/2303.01664/) (2023)
- [Highly Efficient Real-Time Streaming and Fully On-Device Speaker Diarization with Multi-Stage Clustering](https://mlsanity.com/paper/2210.13690/) (2022)

## Abstract (arXiv)

This paper presents a novel study of parameter-free attentive scoring for speaker verification. Parameter-free scoring provides the flexibility of comparing speaker representations without the need of an accompanying parametric scoring model. Inspired by the attention component in Transformer neural networks, we propose a variant of the scaled dot product attention mechanism to compare enrollment and test segment representations. In addition, this work explores the effect on performance of (i) different types of normalization, (ii) independent versus tied query/key estimation, (iii) varying the number of key-value pairs and (iv) pooling multiple enrollment utterance statistics. Experimental results for a 4 task average show that a simple parameter-free attentive scoring mechanism can improve the average EER by 10% over the best cosine similarity baseline.