An analysis of the short utterance problem for speaker characterization

Viñals, Ignacio (Universidad de Zaragoza) ; Ortega, Alfonso (Universidad de Zaragoza) ; Miguel, Antonio (Universidad de Zaragoza) ; Lleida, Eduardo (Universidad de Zaragoza)
An analysis of the short utterance problem for speaker characterization
Resumen: Speaker characterization has always been conditioned by the length of the evaluated utterances. Despite performing well with large amounts of audio, significant degradations in performance are obtained when short utterances are considered. In this work we present an analysis of the short utterance problem providing an alternative point of view. From our perspective the performance in the evaluation of short utterances is highly influenced by the phonetic similarity between enrollment and test utterances. Both enrollment and test should contain similar phonemes to properly discriminate, being degraded otherwise. In this study we also interpret short utterances as incomplete long utterances where some acoustic units are either unbalanced or just missing. These missing units are responsible for the speaker representations to be unreliable. These unreliable representations are biased with respect to the reference counterparts, obtained from long utterances. These undesired shifts increase the intra-speaker variability, causing a significant loss of performance. According to our experiments, short utterances (3-60 s) can perform as accurate as if long utterances were involved by just reassuring the phonetic distributions. This analysis is determined by the current embedding extraction approach, based on the accumulation of local short-time information. Thus it is applicable to most of the state-of-the-art embeddings, including traditional i-vectors and Deep Neural Network (DNN) xvectors.
Idioma: Inglés
DOI: 10.3390/app9183697
Año: 2019
Publicado en: Applied Sciences (Switzerland) 9, 18 (2019), 3697 [19 pp.]
ISSN: 2076-3417

Factor impacto JCR: 2.474 (2019)
Categ. JCR: PHYSICS, APPLIED rank: 62 / 154 = 0.403 (2019) - Q2 - T2
Categ. JCR: ENGINEERING, MULTIDISCIPLINARY rank: 32 / 91 = 0.352 (2019) - Q2 - T2
Categ. JCR: CHEMISTRY, MULTIDISCIPLINARY rank: 88 / 176 = 0.5 (2019) - Q2 - T2
Categ. JCR: MATERIALS SCIENCE, MULTIDISCIPLINARY rank: 161 / 314 = 0.513 (2019) - Q3 - T2

Factor impacto SCIMAGO: 0.418 - Engineering (miscellaneous) (Q1) - Fluid Flow and Transfer Processes (Q2) - Process Chemistry and Technology (Q2) - Instrumentation (Q2) - Materials Science (miscellaneous) (Q2) - Computer Science Applications (Q3)

Financiación: info:eu-repo/grantAgreement/ES/DGA-FEDER/T36-17R
Financiación: info:eu-repo/grantAgreement/ES/DGA-FEDER/2014-2020
Financiación: info:eu-repo/grantAgreement/ES/MINECO/TIN2017-85854-C4-1-R
Tipo y forma: Article (Published version)
Área (Departamento): Área Teoría Señal y Comunicac. (Dpto. Ingeniería Electrón.Com.)

Creative Commons You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.

Exportado de SIDERAL (2023-09-13-10:47:12)

Este artículo se encuentra en las siguientes colecciones:

 Record created 2019-11-13, last modified 2023-09-14

Versión publicada:
Rate this document:

Rate this document:
(Not yet reviewed)