paper-with-me

Papers

A Generative Model for Score Normalization in Speaker Recognition

2017-09-28 · Albert Swart, Niko Brummer

We propose a theoretical framework for thinking about score normalization, which confirms that normalization is not needed under (admittedly fragile) ideal conditions. If, however, these conditions are not met, e.g. under data-set shift between training and runtime, our theory reveals dependencies between scores that could be exploited by strategies such as score normalization. Indeed, it has been demonstrated over and over experimentally, that various ad-hoc score normalization recipes do work. We present a first attempt at using probability theory to design a generative score-space normalization model which gives similar improvements to ZT-norm on the text-dependent RSR 2015 database.

📄 PDF Abstract BibTeX arXiv:1709.09868

Code (0)

등록된 구현이 없습니다.

Tasks

Speaker Recognition

Similar Papers 제목 키워드 기반

Blind score normalization method for PLDA based speaker recognition

2016-02-22 · Danila Doroshin, Nikolay Lubimov, Marina Nastasenko, Mikhail Kotov

Probabilistic Linear Discriminant Analysis (PLDA) has become state-of-the-art method for modeling $i$-vector space in speaker recognition task. However the performance degradation is observed if enrollment data size diff…

Speaker Recognition

LEAP System for SRE19 CTS Challenge -- Improvements and Error Analysis

2020-02-07 · Shreyas Ramoji, Prashant Krishnan, Bhargavram Mysore, Prachi Singh 외

The NIST Speaker Recognition Evaluation - Conversational Telephone Speech (CTS) challenge 2019 was an open evaluation for the task of speaker verification in challenging conditions. In this paper, we provide a detailed a…

Speaker RecognitionSpeaker Verification

Deep Normalization for Speaker Vectors

2020-04-07 · Yunqi Cai, Lantian Li, Dong Wang, Andrew Abel

Deep speaker embedding has demonstrated state-of-the-art performance in speaker recognition tasks. However, one potential issue with this approach is that the speaker vectors derived from deep embedding models tend to be…

Speaker Recognition

Remarks on Optimal Scores for Speaker Recognition

2020-10-10 · Dong Wang

In this article, we first establish the theory of optimal scores for speaker recognition. Our analysis shows that the minimum Bayes risk (MBR) decisions for both the speaker identification and speaker verification tasks …

Speaker IdentificationSpeaker RecognitionSpeaker Verification

The xx205 System for the VoxCeleb Speaker Recognition Challenge 2020

2020-10-31 · Xu Xiang

This report describes the systems submitted to the first and second tracks of the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2020, which ranked second in both tracks. Three key points of the system pipeline are expl…

Speaker Recognition