A short utterance speaker recognition method with improved cepstrum–CNN

A short utterance speaker recognition method with improved cepstrum–CNN

Abstract In this study, an improved cepstrum-convolutional neural network is proposed, which can solve the problem of low recognition accuracy of 1-s short utterance in speaker recognition technology. The audio feature Mel frequency cepstrum coefficient is extracted by using the improved cepstrum al...

Full description

Bibliographic Details
Main Authors: Yongfeng Li, Shuaishuai Chang, QingE Wu
Format: Article
Language:English
Published: Springer 2022-11-01
Series:SN Applied Sciences
Subjects:
Short utterance
Speaker recognition
Mel frequency cepstrum coefficient
Convolutional neural network
Online Access:https://doi.org/10.1007/s42452-022-05227-1

Internet

https://doi.org/10.1007/s42452-022-05227-1

Similar Items