Jam-ALT (JamALT: A Formatting-Aware Lyrics Transcription Benchmark)
Introduced by Cífka et al. in Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark
JamALT is a revision of the JamendoLyrics dataset (80 songs in 4 languages), adapted for use as an automatic lyrics transcription (ALT) benchmark.
The lyrics have been revised according to the newly compiled annotation guide, which include rules about spelling, punctuation, and formatting. The audio is identical to the JamendoLyrics dataset. However, only 79 songs are included, as one of the 20 French songs has been removed due to concerns about potentially harmful content.
Benchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
Jam-ALT English
|
AudioShake
|
|||
|
Jam-ALT
|
AudioShake
|
|||
|
Jam-ALT Spanish
|
AudioShake
|
|||
|
Jam-ALT German
|
AudioShake
|
|||
|
Jam-ALT French
|
Whisper v2
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
