Speaker identification through artificial intelligence techniques: A comprehensive review and research challenges

作者：

Highlights：

• Review of deep learning and machine learning techniques for automatic speaker identification.

• Present Speech databases, pre-processing, feature selection and evaluation methods.

• Present acoustic features, features extraction toolkits and deep learning implementation frameworks.

• Outline Open research challenges presented as future directions.

摘要

•Review of deep learning and machine learning techniques for automatic speaker identification.•Present Speech databases, pre-processing, feature selection and evaluation methods.•Present acoustic features, features extraction toolkits and deep learning implementation frameworks.•Outline Open research challenges presented as future directions.

论文关键词：Speaker identification,Survey,Acoustic features,Artificial Intelligence,Deep learning,Speech databases

论文评审过程：Received 5 February 2020, Revised 7 January 2021, Accepted 7 January 2021, Available online 12 January 2021, Version of Record 6 February 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.114591