mlsanityData to 7 Oct 2026

SongPrep: A Preprocessing Framework and End-to-end Model for Full-song Structure Parsing and Lyrics Transcription

arXiv 2509.17404 ↗First posted 22 Sep 2025eess.AS cs.AI cs.SDcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 15 of its 16 references that are in the map. First posted on arXiv 22 Sep 2025.

Builds on

15 of 16 references.

References · 15

  1. 2022Flow Matching for Generative Modelingcited by 5,426
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  4. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  5. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  6. 2019Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separationcited by 182
  7. 2022Hybrid Transformers for Music Source Separationcited by 134
  8. 2023Zipformer: A faster and better encoder for automatic speech recognitioncited by 77
  9. 2025MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantizationcited by 66
  10. 2024GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Taskscited by 29
  11. 2023All-In-One Metrical And Functional Structure Analysis With Neighborhood Attentions on Demixed Audiocited by 27
  12. 2025LeVo: High-Quality Song Generation with Multi-Preference Alignmentcited by 23
3 more
  1. 2025SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinementcited by 21
  2. 2023AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Datacited by 16
  3. 2025Towards Hallucination-Free Music: A Reinforcement Learning Preference Optimization Framework for Reliable Song Generationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessmentcited by 6
  2. 2026LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Trainingcited by 4
  3. 2026Tutti: Expressive Multi-Singer Synthesis via Structure-Level Timbre Control and Vocal Texture Modelingcited by 0
  4. 2026VocalParse: Towards Unified and Scalable Singing Voice Transcription with Large Audio Language Modelscited by 0
  5. 2026MPEcho: A Melody and Phoneme-Aware Generative Framework for Controllable Cover Song Generationcited by 0