Credits

LyriSync is built on published research and open-source software. None of it requires a credit. It gets one anyway.

Alignment

The default aligner is the multi-task model by Jiawen Huang, Emmanouil Benetos and Sebastian Ewert, released under the MIT licence at github.com/jhuang448/LyricsAlignment-MTL.

Huang, J., Benetos, E. and Ewert, S. (2022). Improving Lyrics Alignment Through Joint Pitch Detection. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2022), pp. 451-455.

A second aligner, and the check LyriSync runs on every track for an untranscribed intro, come from the phoneme-level model by Kilian Schulze-Forster and colleagues, released under the MIT licence at github.com/schufo/lyrics-aligner.

Schulze-Forster, K., Doire, C. S. J., Richard, G. and Badeau, R. (2021). Phoneme Level Lyrics Alignment and Text-Informed Singing Voice Separation. IEEE/ACM Transactions on Audio, Speech and Language Processing, 29, pp. 2382-2395.

Vocal separation

The vocal is isolated from the mix with Hybrid Transformer Demucs by Meta AI Research, released under the MIT licence at github.com/facebookresearch/demucs.

Rouard, S., Massa, F. and Defossez, A. (2023). Hybrid Transformers for Music Source Separation. ICASSP 2023.

Everything else

PyTorch, librosa, NumPy, SciPy, NLTK, the CMU Pronouncing Dictionary, FFmpeg, Next.js, React, Supabase and the Unbounded, Hanken Grotesk and DM Mono typefaces, each under its own permissive or open licence. The fonts are served from LyriSync's own servers, not Google's.

Training data for the three models above was assembled by their authors from academic datasets. LyriSync does not hold, and has never held, any of it. What LyriSync does with your own audio, and for how long, is set out in the Privacy Policy; the words you paste are never used for anything but timing them.