TART is a modular four‑stage pipeline that transcribes guitar audio into tablature, addressing key limitations of existing systems such as missing expressive techniques, incorrect string‑fret assignments, and poor performance on noisy recordings. The stages include an audio‑to‑MIDI model, an expressive technique classifier, an audio‑conditioned T5 encoder‑decoder for string‑fret mapping, and an automated tablature generator. In zero‑shot evaluations on GuitarSet, EGDB, and noisy variants, TART outperforms prior baselines with significant gains in audio‑to‑MIDI, string‑fret, and end‑to‑end tablature metrics.
By Akshaj Gupta, Hwi Joo Park, Andrea Guzman, Shamak Gowda, Samhita Konduri, Jiachen Lian, Robin Netzorg, Gopala Anumanchipalli
arXiv:2607. 18303v1 Announce Type: cross Abstract: Identifying which string produces a given pitch in monophonic electric guitar audio is a fundamental classification challenge: a single pitch can often be produced on multiple strings at different fret positions, with timbral differences that prior listening studies confirm are largely imperceptible to untrained humans.
By Aadi Garg
arXiv:2606. 30700v1 Announce Type: cross Abstract: Self-supervised learning enables audio representations that transfer across domains and tasks.
By Ludovic K. Tuncay (IRIT-SAMoVA), Etienne Labb\'e (IRIT-SAMoVA), Thomas Pellegrini (IRIT-SAMoVA)
arXiv:2607. 23395v1 Announce Type: cross Abstract: Music Source Separation (MSS), the task of recovering individual sound components (stems) from a polyphonic mixture, is central to applications ranging from karaoke and remixing to audio restoration and content production.
By Roman Solovyev, Ilya Kiselev, Alexander Stempkovskiy, Tatiana Gabruseva
The paper introduces a lightweight technique to steer the pitch content of audio generated by the Stable Audio Open diffusion model. A small convolutional probe (~125k parameters) is trained to decode frame‑level pitch‑class activations from the model’s latent space using paired audio and MIDI data. During inference, the frozen probe acts as a differentiable loss, guiding generation toward a user‑specified pitch‑class sequence without retraining the base model, and improves melodic coherence by 2.4× over the unguided baseline.
By Yushi Ye, Wilson Zheng, Yongyi Zang
arXiv:2508.03448v4 Announce Type: replace-cross
Abstract: Music recordings often suffer from audio quality issues such as excessive reverberation, distortion, clipping, tonal imbalances, and a narrow...
By Jan Melechovsky, Ambuj Mehrish, Abhinaba Roy, Dorien Herremans
arXiv:2608. 03920v1 Announce Type: cross Abstract: Humans recognize a musical passage even when it is shifted in time or transposed in pitch, indicating a notion of equivariance in the representation space.
By Zixun Guo, Simon Dixon
arXiv:2608. 14819v1 Announce Type: cross Abstract: Music foundation models are commonly used as frozen audio feature extractors, yet selecting which layer to extract from remains largely heuristic.
By Angelos-Nikolaos Kanatas, Yuexuan Kong, Pablo Alonso-Jim\'enez, Xavier Serra, Dmitry Bogdanov
Generalizable Audio-to-Score (A2S) transcription is fundamentally constrained by the severe scarcity of high-quality, real-world paired data. Relying solely on existing human-annotated datasets often...
TUTTI is a new pre‑training framework for audio‑to‑score transcription that uses a large, fully synthetic multi‑instrument dataset generated by a symbolic music model. The approach trains a standard Transformer encoder‑decoder on these synthetic audio‑score pairs, producing a stronger foundational representation than single‑instrument training. When fine‑tuned on real datasets, TUTTI surpasses prior methods, achieving state‑of‑the‑art results and demonstrating strong cross‑instrument transferability.
By Jianhuai Hu, Yashan Wang, Shangda Wu, Zhancheng Guo, Shijie Liang, Wuna Meng, Chuanqi Yang, Xiaobing Li, Feng Yu, Maosong Sun
DuoTok is a source‑aware dual‑track music tokenizer designed for vocal‑accompaniment generation. It first learns a semantic audio representation via self‑supervised pretraining, then refines source‑aware structure with feature‑replacement noise and multi‑task supervision (spectral reconstruction, source separation regularization, and an ASR head for lyric alignment). The encoder is frozen and hard‑routed codebooks for vocals and accompaniment are learned, while a diffusion decoder restores fine acoustic detail from the discrete tokens, achieving a favorable predictability‑fidelity trade‑off at ultra‑low bitrate across public benchmarks.
By Rui Lin, Zhiyue Wu, Jiahe Lei, Kangdi Wang, Weixiong Chen, Junyu Dai, Tao Jiang
arXiv:2603. 07584v2 Announce Type: replace-cross Abstract: Computational engine sound modeling is central to the automotive audio industry, particularly for active sound design applications and virtual prototyping.
By Robin Doerfler, Lonce Wyse