A method to compensate the influence of speech codec in speaker recognition

• Published in: International journal of speech technology Vol. 21; no. 4; pp. 975 - 985
• Main Authors: Calvo de Lara, José R., Reyes Diaz, Flavio J., Hernández Sierra, Gabriel, Jimenez Alcazar, Orlando
• Format: Journal Article
• Language: English
• Published: New York Springer US 15.12.2018; Springer Nature B.V
• Subjects: Artificial Intelligence; Cellular communication; Codec; Computer mediated communication; Decoding; Engineering; Error analysis; Internet; Online banking; Signal,Image and Speech Processing; Social Sciences; Speaker identification; Speech disorders; Speech recognition; Voice communication; Voice recognition; Voice codec; Speaker recognition; Linear discriminant analysis; i-Vector representation; Variability compensation

The recognition of a person by his voice or “speaker recognition”, is a biometric specialty increasingly used in electronic commerce and electronic banking transactions and forensic investigations, among others. Speaker recognition is supported by the discriminative information contained in the spee...