Text-independent Speaker Recognition Based on X-vector

Zhou, Lianyu; Wang, Mingjiang; Qian, Yukun; Luo, Huaiwen; Li, Heng; Lin, Xu

doi:10.1109/icsip55141.2022.9887021

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

Publication Types

Select...

Other1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The basic classic machine learning methodologies used for this problem are UBM-GMM (Universal Background Model -Gaussian Mixture Model) and "i-vectors" [5], [6], [7]. An early solution based on deep neural networks is the "x-vector" [8], [9], [10] network. Other deep network architectures, such as LSTM [11] or ResNet [12], were also proposed for this purpose.…”

Section: Introductionmentioning

confidence: 99%

Automatic speaker's age classification in the Common Voice database

Nowakowski,

Kasprzak

2023

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

An approach to speaker's age classification using deep neural networks is described. Preliminary signal features are extracted, based on mel-frequency cepstral coefficients (MFCC). For gender classification an MLP network appears to be a satisfactory lightweight solution. For the age modelling and classification problem, two network types, ResNet34 and xvectors, were tested and compared. The impact of signal processing parameters and gender information (both theoretic perfect realistic imperfect) onto the age classification performance was experimentally studied. The neural networks were trained and verified on the large "Common Voice" dataset of English speech recordings.

show abstract