Feature extraction from AI generated songs

Mo Adda; Nancy Scheidt; Alexander Gegov; Fahad Ahmad; Pravin Ram Sivaraman; Alexandar Ichtev

doi:10.1109/ICARAI70085.2026.11635738

Feature extraction from AI generated songs

Mo Adda^*
, Nancy Scheidt
, Alexander Gegov
, Fahad Ahmad
, Pravin Ram Sivaraman
, Alexandar Ichtev

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper introduces a forensic framework for detecting AI-generated lyrical and melodic audio using MFCC features, similarity metrics, and multi-algorithm fusion. Tests on 500 samples achieved 95% accuracy in distinguishing human from synthetic audio. The system offers a transparent and efficient method for audio authenticity verification in digital forensics and AI-content detection.

Original language	English
Title of host publication	International Conference Automatics, Robotics and Artificial Intelligence, ICARAI 2026 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Number of pages	5
ISBN (Electronic)	9798331563110
ISBN (Print)	9798331563127
DOIs	https://doi.org/10.1109/ICARAI70085.2026.11635738
Publication status	Published - 10 Aug 2026
Event	4th International Conference Automatics, Robotics and Artificial Intelligence, ICARAI 2026 - Sozopol, Bulgaria Duration: 12 Jun 2026 → 15 Jun 2026

Conference

Conference	4th International Conference Automatics, Robotics and Artificial Intelligence, ICARAI 2026
Country/Territory	Bulgaria
City	Sozopol
Period	12/06/26 → 15/06/26

Keywords

AI detection
Fusion algorithms
Machine learning
MFCC
Music forensics
Song authenticity

Access to Document

10.1109/ICARAI70085.2026.11635738

Cite this

@inproceedings{dd4729818c2a47f486ed11394ceee9f8,

title = "Feature extraction from AI generated songs",

abstract = "This paper introduces a forensic framework for detecting AI-generated lyrical and melodic audio using MFCC features, similarity metrics, and multi-algorithm fusion. Tests on 500 samples achieved 95\% accuracy in distinguishing human from synthetic audio. The system offers a transparent and efficient method for audio authenticity verification in digital forensics and AI-content detection.",

keywords = "AI detection, Fusion algorithms, Machine learning, MFCC, Music forensics, Song authenticity",

author = "Mo Adda and Nancy Scheidt and Alexander Gegov and Fahad Ahmad and Sivaraman, \{Pravin Ram\} and Alexandar Ichtev",

note = "No ISSN; 4th International Conference Automatics, Robotics and Artificial Intelligence, ICARAI 2026 ; Conference date: 12-06-2026 Through 15-06-2026",

year = "2026",

month = aug,

day = "10",

doi = "10.1109/ICARAI70085.2026.11635738",

language = "English",

isbn = "9798331563127",

booktitle = "International Conference Automatics, Robotics and Artificial Intelligence, ICARAI 2026 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

}

Adda, M, Scheidt, N, Gegov, A , Ahmad, F, Sivaraman, PR & Ichtev, A 2026, Feature extraction from AI generated songs. in International Conference Automatics, Robotics and Artificial Intelligence, ICARAI 2026 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 4th International Conference Automatics, Robotics and Artificial Intelligence, ICARAI 2026, Sozopol, Bulgaria, 12/06/26. https://doi.org/10.1109/ICARAI70085.2026.11635738

TY - GEN

T1 - Feature extraction from AI generated songs

AU - Adda, Mo

AU - Scheidt, Nancy

AU - Gegov, Alexander

AU - Ahmad, Fahad

AU - Sivaraman, Pravin Ram

AU - Ichtev, Alexandar

N1 - No ISSN

PY - 2026/8/10

Y1 - 2026/8/10

N2 - This paper introduces a forensic framework for detecting AI-generated lyrical and melodic audio using MFCC features, similarity metrics, and multi-algorithm fusion. Tests on 500 samples achieved 95% accuracy in distinguishing human from synthetic audio. The system offers a transparent and efficient method for audio authenticity verification in digital forensics and AI-content detection.

AB - This paper introduces a forensic framework for detecting AI-generated lyrical and melodic audio using MFCC features, similarity metrics, and multi-algorithm fusion. Tests on 500 samples achieved 95% accuracy in distinguishing human from synthetic audio. The system offers a transparent and efficient method for audio authenticity verification in digital forensics and AI-content detection.

KW - AI detection

KW - Fusion algorithms

KW - Machine learning

KW - MFCC

KW - Music forensics

KW - Song authenticity

UR - https://www.scopus.com/pages/publications/105048059352

U2 - 10.1109/ICARAI70085.2026.11635738

DO - 10.1109/ICARAI70085.2026.11635738

M3 - Conference contribution

AN - SCOPUS:105048059352

SN - 9798331563127

BT - International Conference Automatics, Robotics and Artificial Intelligence, ICARAI 2026 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 4th International Conference Automatics, Robotics and Artificial Intelligence, ICARAI 2026

Y2 - 12 June 2026 through 15 June 2026

ER -

Feature extraction from AI generated songs

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this