Saved in:
Bibliographic Details
Main Authors: Wang, Quan, Moreno, Ignacio Lopez
Format: Preprint
Published: 2020
Subjects:
Online Access:https://arxiv.org/abs/2007.12069
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929385784737792
author Wang, Quan
Moreno, Ignacio Lopez
author_facet Wang, Quan
Moreno, Ignacio Lopez
contents This paper discusses one of the most challenging practical engineering problems in speaker recognition systems - the version control of models and user profiles. A typical speaker recognition system consists of two stages: the enrollment stage, where a profile is generated from user-provided enrollment audio; and the runtime stage, where the voice identity of the runtime audio is compared against the stored profiles. As technology advances, the speaker recognition system needs to be updated for better performance. However, if the stored user profiles are not updated accordingly, version mismatch will result in meaningless recognition results. In this paper, we describe different version control strategies for speaker recognition systems that had been carefully studied at Google from years of engineering practice. These strategies are categorized into three groups according to how they are deployed in the production environment: device-side deployment, server-side deployment, and hybrid deployment. To compare different strategies with quantitative metrics under various network configurations, we present SpeakerVerSim, an easily-extensible Python-based simulation framework for different server-side deployment strategies of speaker recognition systems.
format Preprint
id arxiv_https___arxiv_org_abs_2007_12069
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Version Control of Speaker Recognition Systems
Wang, Quan
Moreno, Ignacio Lopez
Audio and Speech Processing
Distributed, Parallel, and Cluster Computing
Networking and Internet Architecture
Software Engineering
This paper discusses one of the most challenging practical engineering problems in speaker recognition systems - the version control of models and user profiles. A typical speaker recognition system consists of two stages: the enrollment stage, where a profile is generated from user-provided enrollment audio; and the runtime stage, where the voice identity of the runtime audio is compared against the stored profiles. As technology advances, the speaker recognition system needs to be updated for better performance. However, if the stored user profiles are not updated accordingly, version mismatch will result in meaningless recognition results. In this paper, we describe different version control strategies for speaker recognition systems that had been carefully studied at Google from years of engineering practice. These strategies are categorized into three groups according to how they are deployed in the production environment: device-side deployment, server-side deployment, and hybrid deployment. To compare different strategies with quantitative metrics under various network configurations, we present SpeakerVerSim, an easily-extensible Python-based simulation framework for different server-side deployment strategies of speaker recognition systems.
title Version Control of Speaker Recognition Systems
topic Audio and Speech Processing
Distributed, Parallel, and Cluster Computing
Networking and Internet Architecture
Software Engineering
url https://arxiv.org/abs/2007.12069