Pith. sign in

REVIEW 4 cited by

Mel-Band RoFormer for Music Source Separation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.01809 v1 pith:I37FSKML submitted 2023-10-03 cs.SD eess.AS

classification cs.SDeess.AS
keywords band-splitbs-roformerbsrnnmodelschemeseparationmel-bandmel-roformer
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recently, multi-band spectrogram-based approaches such as Band-Split RNN (BSRNN) have demonstrated promising results for music source separation. In our recent work, we introduce the BS-RoFormer model which inherits the idea of band-split scheme in BSRNN at the front-end, and then uses the hierarchical Transformer with Rotary Position Embedding (RoPE) to model the inner-band and inter-band sequences for multi-band mask estimation. This model has achieved state-of-the-art performance, but the band-split scheme is defined empirically, without analytic supports from the literature. In this paper, we propose Mel-RoFormer, which adopts the Mel-band scheme that maps the frequency bins into overlapped subbands according to the mel scale. In contract, the band-split mapping in BSRNN and BS-RoFormer is non-overlapping and designed based on heuristics. Using the MUSDB18HQ dataset for experiments, we demonstrate that Mel-RoFormer outperforms BS-RoFormer in the separation tasks of vocals, drums, and other stems.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. YingMusic-Singer: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance

    eess.AS 2026-03 unverdicted novelty 7.0 of 10

    YingMusic-Singer-Plus is a diffusion model for singing voice synthesis that preserves melody from a reference clip while allowing flexible lyric changes without manual alignment, outperforming Vevo2 and introducing th...

  2. StemFX: Learning Mixing Style Representations via Autoregressive FX Chain Prediction on Source-Separated Stems

    cs.SD 2026-07 conditional novelty 6.0 of 10

    StemFX predicts tokenized per-stem audio-effect chains with a jointly-trained Transformer encoder-decoder, beating contrastive and prior FX-encoding methods on effect-chain retrieval and real-mix style transfer.

  3. DualDub: Video-to-Soundtrack Generation via Joint Speech and Background Audio Synthesis

    cs.MM 2025-07 conditional novelty 6.0 of 10

    A single multimodal language model can generate intelligible speech and synchronized background audio jointly from a silent video, transcript, and reference voice, outperforming separately concatenated speech and audi...

  4. Music-Source-Separation-Training (MSST): A Unified Framework for Training and Evaluating Music Demixing Models

    cs.SD 2026-07 conditional novelty 3.5 of 10

    MSST unifies training, validation, and inference for many music source-separation architectures and reports small quality gains from TTA, ensembling, and related engineering techniques.

Pith tools