SongPrep: A Preprocessing Framework and End-to-end Model for Full-song Structure Parsing and Lyrics Transcription
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909799475576832 |
|---|---|
| author | Tan, Wei Lei, Shun Zhang, Huaicheng Li, Guangzheng Zhang, Yixuan Chen, Hangting Yu, Jianwei Gu, Rongzhi Yu, Dong |
| author_facet | Tan, Wei Lei, Shun Zhang, Huaicheng Li, Guangzheng Zhang, Yixuan Chen, Hangting Yu, Jianwei Gu, Rongzhi Yu, Dong |
| contents | Artificial Intelligence Generated Content (AIGC) is currently a popular research area. Among its various branches, song generation has attracted growing interest. Despite the abundance of available songs, effective data preparation remains a significant challenge. Converting these songs into training-ready datasets typically requires extensive manual labeling, which is both time consuming and costly. To address this issue, we propose SongPrep, an automated preprocessing pipeline designed specifically for song data. This framework streamlines key processes such as source separation, structure analysis, and lyric recognition, producing structured data that can be directly used to train song generation models. Furthermore, we introduce SongPrepE2E, an end-to-end structured lyrics recognition model based on pretrained language models. Without the need for additional source separation, SongPrepE2E is able to analyze the structure and lyrics of entire songs and provide precise timestamps. By leveraging context from the whole song alongside pretrained semantic knowledge, SongPrepE2E achieves low Diarization Error Rate (DER) and Word Error Rate (WER) on the proposed SSLD-200 dataset. Downstream tasks demonstrate that training song generation models with the data output by SongPrepE2E enables the generated songs to closely resemble those produced by humans. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17404 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SongPrep: A Preprocessing Framework and End-to-end Model for Full-song Structure Parsing and Lyrics Transcription Tan, Wei Lei, Shun Zhang, Huaicheng Li, Guangzheng Zhang, Yixuan Chen, Hangting Yu, Jianwei Gu, Rongzhi Yu, Dong Audio and Speech Processing Artificial Intelligence Sound Artificial Intelligence Generated Content (AIGC) is currently a popular research area. Among its various branches, song generation has attracted growing interest. Despite the abundance of available songs, effective data preparation remains a significant challenge. Converting these songs into training-ready datasets typically requires extensive manual labeling, which is both time consuming and costly. To address this issue, we propose SongPrep, an automated preprocessing pipeline designed specifically for song data. This framework streamlines key processes such as source separation, structure analysis, and lyric recognition, producing structured data that can be directly used to train song generation models. Furthermore, we introduce SongPrepE2E, an end-to-end structured lyrics recognition model based on pretrained language models. Without the need for additional source separation, SongPrepE2E is able to analyze the structure and lyrics of entire songs and provide precise timestamps. By leveraging context from the whole song alongside pretrained semantic knowledge, SongPrepE2E achieves low Diarization Error Rate (DER) and Word Error Rate (WER) on the proposed SSLD-200 dataset. Downstream tasks demonstrate that training song generation models with the data output by SongPrepE2E enables the generated songs to closely resemble those produced by humans. |
| title | SongPrep: A Preprocessing Framework and End-to-end Model for Full-song Structure Parsing and Lyrics Transcription |
| topic | Audio and Speech Processing Artificial Intelligence Sound |
| url | https://arxiv.org/abs/2509.17404 |