Pith. sign in

Current AI music generation models typically rely on two main components working in sequence

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.SD 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

background 1

representative citing papers

AI-Generated Song Detection via Lyrics Transcripts

cs.SD · 2025-06-23 · conditional · novelty 6.0

Transcribing audio with Whisper and classifying the transcript with LLM2Vec detects AI-generated songs from audio alone, nearly matching clean-lyrics accuracy and beating audio-based detectors under perturbations and on unseen generators.

citing papers explorer

Showing 1 of 1 citing paper.

  • AI-Generated Song Detection via Lyrics Transcripts cs.SD · 2025-06-23 · conditional · none · ref 2

    Transcribing audio with Whisper and classifying the transcript with LLM2Vec detects AI-generated songs from audio alone, nearly matching clean-lyrics accuracy and beating audio-based detectors under perturbations and on unseen generators.