Project Qualia investigates whether experiential similarity between songs can be extracted from listening behavior. Using 1.29 billion scrobbles from 9,396 users, the authors trained a Word2Vec model (Song2Vec) on session data, then applied an artist‑residual procedure to isolate artist‑independent signals. The residual embeddings still contained strong cross‑artist similarity, forming coherent genre and era clusters, demonstrating that experiential structure exists beyond artist identity.
arXiv:2506. 14293v4 Announce Type: replace-cross Abstract: We present Sleeping-DISCO 9M, a large-scale pre-training dataset for music and song.
arXiv:2602.12881v2 Announce Type: replace-cross Abstract: We examine how lyric representation shapes computational similarity using four 384-dimensional multilingual MiniLM representations of 7,891 K...
MUUNRiver-Bench is a diagnostic benchmark for music retrieval that uses natural‑language instructions to define relevance for reference‑audio queries. It contains 3,440 tracks across 13 genres and 116 sub‑genres and covers seven tasks such as similar‑music, style‑preserving lyric‑rewriting, cover, and segment retrieval. Experiments with six models in eight configurations show that acoustic encoders favor local identity while text‑aligned encoders favor semantic relations, and that instruction‑aware and audio‑text fusion systems do not consistently outperform their backbones.
The paper investigates whether expert critic‑sourced relationships between musical artists—called critical adjacency—can be recovered from the artists’ acoustic content. By modeling artists as distributions over 80 low‑level acoustic descriptors and measuring pairwise proximity with Wasserstein distances, the authors achieve an out‑of‑sample AUC of 0.767 for predicting critic‑linked edges, with higher recoverability for edges supported by multiple critics. The results suggest that critical discourse contains a reproducible sonic core, while sociological factors also influence the perceived adjacency between artists.
arXiv:2607. 27909v1 Announce Type: cross Abstract: Objective evaluation of expressive MIDI piano performances typically relies on attribute statistics such as timing, velocity, and duration of individual notes.
arXiv:2609.39552v1 Announce Type: cross Abstract: Text-to-song generation models can be prompted to imitate specific artists or regurgitate entire songs from their training data. Although these pheno...
arXiv:2607. 22413v1 Announce Type: cross Abstract: Sample retrieval tools can help composers find harmonically compatible material, but querying from a fixed reference sample becomes less informative as arrangements evolve and the harmonic context shifts with each musical decision.
The paper introduces the MATCHA dataset, comprising 1,105 perceptual assessments from 83 experts on attribute-based music matches across five musical attributes—melody, harmony, rhythm, voice, and timbre. A triplet-based forced-choice experiment with 300 cases, including plagiarism, cover songs, and AI-generated music, was used to gather these judgments. Results show measurable agreement among participants and partial alignment with computational similarity measures, highlighting the need for perceptually grounded evaluation in generative AI for music.
A tutorial monograph on generative models for music audio covers a wide range of applications—from instrumental clips and full songs with vocals to edits of existing recordings and real‑time accompaniment systems. It explains neural audio codecs, autoencoders, autoregressive and masked token models, diffusion and flow matching, sampling acceleration, and preference optimization, linking training objectives to published systems through worked examples. The book also discusses musical requirements for different tasks, compares representations and methods, and addresses evaluation, data provenance, memorization, attribution, and legal implications.
arXiv:2607. 00777v1 Announce Type: cross Abstract: Recognizing jazz standards from audio is a challenging form of tune-level music retrieval: different performances of the same standard may vary in tempo, key, arrangement, instrumentation, improvisational content, and even whether the head melody is present.
Gangqinpu is a large, multi‑genre piano dataset that provides aligned audio, MIDI, and musical scores for 18,786 pieces, covering pop, classical, jazz, folk/traditional, rock, and blues. The dataset includes automatic note‑level alignments, beat/downbeat annotations, genre labels, and a binary classifier to filter non‑expressive performances. It is designed to reduce data leakage with ASAP splits and has shown cross‑dataset improvements in beat tracking and in‑domain gains for transcription and expressive performance rendering.
Objective evaluation of expressive MIDI piano performances typically relies on attribute statistics such as timing, velocity, and duration of individual notes. However, these methods often disregard dependencies between notes, which poses a potential limitation in assessing the similarity between two sets of performances.