Parameter-Free Attentive Scoring for Speaker Verification
Not on the map. Why?
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.
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
21 of 43 references.
References · 21
- 2017Attention Is All You Needcited by 60,361
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2015Distilling the Knowledge in a Neural Networkcited by 10,324
- 2016Layer Normalizationcited by 5,669
- 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
- 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 628
- 2017Generalized End-to-End Loss for Speaker Verificationcited by 293
- 2019Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modelingcited by 86
- 2015End-to-End Text-Dependent Speaker Verificationcited by 49
- 2019CN-CELEB: a challenging Chinese speaker recognition datasetcited by 48
- 2020Self-attention encoding and pooling for speaker recognitioncited by 33
- 2017Attention-Based Models for Text-Dependent Speaker Verificationcited by 17
9 more
- 2020Probabilistic embeddings for speaker diarizationcited by 11
- 2021Dr-Vectors: Decision Residual Networks and an Improved Loss for Speaker Recognitioncited by 10
- 2020S-vectors and TESA: Speaker Embeddings and a Speaker Authenticator Based on Transformer Encodercited by 8
- 2021Multi-View Self-Attention Based Transformer for Speaker Recognitioncited by 8
- 2020Version Control of Speaker Recognition Systemscited by 6
- 2020Graph Attention Networks for Speaker Verificationcited by 6
- 2022Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speechcited by 6
- 2020Text-Independent Speaker Verification with Dual Attention Networkcited by 3
- 2021Improving Speaker Identification for Shared Devices by Adapting Embeddings to Speaker Subsetscited by 3
Built on by
Citing papers per year: 2022: 1; 2023: 1.
2 papers.