Self-supervised speaker embeddings

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F19%3APU134182" target="_blank" >RIV/00216305:26230/19:PU134182 - isvavai.cz</a>

Result on the web

<a href="https://www.isca-speech.org/archive/Interspeech_2019/pdfs/2842.pdf" target="_blank" >https://www.isca-speech.org/archive/Interspeech_2019/pdfs/2842.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.21437/Interspeech.2019-2842" target="_blank" >10.21437/Interspeech.2019-2842</a>

Result language

angličtina

Original language name

Self-supervised speaker embeddings

Original language description

Contrary to i-vectors, speaker embeddings such as x-vectors are incapable of leveraging unlabelled utterances, due to the classification loss over training speakers. In this paper, we explore an alternative training strategy to enable the use of unlabelled utterances in training. We propose to train speaker embedding extractors via reconstructing the frames of a target speech segment, given the inferred embedding of another speech segment of the same utterance. We do this by attaching to the standard speaker embedding extractor a decoder network, which we feed not merely with the speaker embedding, but also with the estimated phone sequence of the target frame sequence. The reconstruction loss can be used either as a single objective, or be combined with the standard speaker classification loss. In the latter case, it acts as a regularizer, encouraging generalizability to speakers unseen during training. In all cases, the proposed architectures are trained from scratch and in an endto- end fashion. We demonstrate the benefits from the proposed approach on the VoxCeleb and Speakers in the Wild Databases, and we report notable improvements over the baseline.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2019

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of Interspeech

ISBN

—

ISSN

1990-9772

e-ISSN

—

Number of pages

5

Pages from-to

2863-2867

Publisher name

International Speech Communication Association

Place of publication

Graz

Event location

INTERSPEECH 2019

Event date

Sep 15, 2019

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000831796403001