cs.SD · 2026-07-12 · No. 51

Sound, 2026-07-12.

4 new papers in cs.SD. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

4 entries
  1. 01

    MulTTiPop: A Multitrack Transcription Dataset for Pop Music

    Nathan Pruyne, Benjamin Stoler, William Chen, Chien-yu Huang, Shinji Watanabe, Chris Donahue

    cs.SD · cs.LG

    We present MulTTiPop, a dataset of pop music segments and their associated multitrack MIDI recordings for the evaluation of automatic music transcription models. MulTTiPop contains 572 segments of popular music totaling 3.5 hours of audio, and contains songs from diverse genres and decades from the 1930s to 2000s. To collect this dataset, we perform metadata-based matching on song segments from the Lakh MIDI and TheoryTab datasets, manually...

    arxiv.org/abs/2607.08756 · PDF

  2. 02

    Structural Bottlenecks on Frequency Representation in End-to-End Audio Models

    Nicole Cosme-Clifford

    cs.SD · cs.LG

    End-to-end neural audio models achieve high-fidelity compression and generation. We might read that performance as evidence they directly represent interpretable features such as pitch and timbre, but a model can produce plausible outputs without doing so. A model may encode these features in any reachable basis, but regardless of which, the features are well described as compositions of time-frequency-localized primitives. Whether...

    arxiv.org/abs/2607.08545 · PDF

  3. 03

    MuScriptor: An Open Model for Multi-Instrument Music Transcription

    Simon Rouard, Michael Krause, Axel Roebel, Carl-Johann Simon-Gabriel, Alexandre Défossez

    cs.SD · cs.LG

    Existing methods for automatic music transcription are often limited to single-instrument recordings or fail on complex, real music mixes. Although previous work utilizes synthetic training data, the resulting models generalize poorly, leading to largely unusable transcription output in realistic, multi-instrument settings. In this work, we analyze the effectiveness of synthetic data for pre-training while combining it with fine-tuning on...

    arxiv.org/abs/2607.08168 · PDF

  4. 04

    PS4: Proxy-Supervised Joint Training for Real Target Speaker Extraction

    Wanyi Ning, Wei Zhou, Yingpeng Li, Yinshang Guo, Haitao Qian, Yiming Cheng

    cs.SD · cs.AI

    Training target speaker extraction (TSE) models for real conversational mixtures remains challenging because large-scale training corpora and clean target speech for supervision are unavailable. We present PS4, a proxy-supervised training framework for TSE in real conversational mixtures, with two main contributions. First, we construct a large-scale corpus of 71,771 training samples derived from four public datasets, covering both Chinese...

    arxiv.org/abs/2607.08111 · PDF

This edition is part of The Daily Abstract — cs.SD archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.