VietLyrics: A Large-Scale Dataset and Models for Vietnamese Automatic Lyrics Transcription
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918256605921280 |
|---|---|
| author | Nguyen, Quoc Anh Cheng, Bernard Soh, Kelvin |
| author_facet | Nguyen, Quoc Anh Cheng, Bernard Soh, Kelvin |
| contents | Automatic Lyrics Transcription (ALT) for Vietnamese music presents unique challenges due to its tonal complexity and dialectal variations, but remains largely unexplored due to the lack of a dedicated dataset. Therefore, we curated the first large-scale Vietnamese ALT dataset (VietLyrics), comprising 647 hours of songs with line-level aligned lyrics and metadata to address these issues. Our evaluation of current ASRbased approaches reveal significant limitations, including frequent transcription errors and hallucinations in non-vocal segments. To improve performance, we fine-tuned Whisper models on the VietLyrics dataset, achieving superior results compared to existing multilingual ALT systems, including LyricWhiz. We publicly release VietLyrics and our models, aiming to advance Vietnamese music computing research while demonstrating the potential of this approach for ALT in low-resource language and music. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_22295 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VietLyrics: A Large-Scale Dataset and Models for Vietnamese Automatic Lyrics Transcription Nguyen, Quoc Anh Cheng, Bernard Soh, Kelvin Artificial Intelligence Computation and Language Automatic Lyrics Transcription (ALT) for Vietnamese music presents unique challenges due to its tonal complexity and dialectal variations, but remains largely unexplored due to the lack of a dedicated dataset. Therefore, we curated the first large-scale Vietnamese ALT dataset (VietLyrics), comprising 647 hours of songs with line-level aligned lyrics and metadata to address these issues. Our evaluation of current ASRbased approaches reveal significant limitations, including frequent transcription errors and hallucinations in non-vocal segments. To improve performance, we fine-tuned Whisper models on the VietLyrics dataset, achieving superior results compared to existing multilingual ALT systems, including LyricWhiz. We publicly release VietLyrics and our models, aiming to advance Vietnamese music computing research while demonstrating the potential of this approach for ALT in low-resource language and music. |
| title | VietLyrics: A Large-Scale Dataset and Models for Vietnamese Automatic Lyrics Transcription |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2510.22295 |