Spectrogram-Based Detection of Auto-Tuned Vocals in Music Recordings

In the domain of music production and audio processing, the implementation of automatic pitch correction of the singing voice, also known as Auto-Tune, has significantly transformed the landscape of vocal performance. While autotuning technology has offered musicians the ability to tune their vocal pitches and achieve a desired level of precision, its use has also sparked debates regarding its impact on authenticity and artistic integrity. As a result, detecting and analyzing AutoTuned vocals in music recordings has become valuable for music scholars, producers, and listeners. However, to the best of our knowledge, no prior effort has been made in this direction. This study introduces a data-driven approach leveraging triplet networks for the detection of Auto-Tuned songs, backed by the creation of a dataset composed of original and Auto-Tuned audio clips. The experimental results demonstrate the superiority of the proposed method in terms of both accuracy and robustness when compared to two baseline models: Rawnet2, an end-to-end model proposed for anti-spoofing and widely used for other audio forensic tasks, and a Graph Attention Transformer-based approach specifically designed for singing vocal deepfake detection.