@inproceedings{au-2026-midi,
    title = "{MIDI}-{PHOR}: Multi-View Distillation for Music Understanding and Captioning",
    author = "Au, Steven",
    editor = "Epure, Elena V.  and
      Oramas, Sergio  and
      Doh, SeungHeon  and
      Ramoneda, Pedro  and
      Kruspe, Anna  and
      Sordo, Mohamed",
    booktitle = "Proceedings of the 4th Workshop on {NLP} for Music and Audio ({NLP}4{M}us{A} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-cite/2026.nlp4musa-1.6/",
    doi = "10.18653/v1/2026.nlp4musa-1.6",
    pages = "33--43",
    ISBN = "979-8-89176-369-2",
    abstract = "A central limitation of current music understanding frameworks is the reliance on audio embeddings, which frequently yields interpretations lacking traceable ties to explicit musical elements such as notes, dynamics, and instrumentation. We address this gap with MIDIPHOR, a MIDI-first framework that converts symbolic data into structured, queryable representations for reasoning. MIDI-PHOR distills each piece into three complementary views: a symbolic view capturing pitch, meter, and key; a time-series (TS) view that tracks rhythmic salience, texture, and role activity; and an instrument-role graph encoding ensemble interactions. With evidence-linked claims, experiments demonstrate reduced hallucinations compared to raw-MIDI baselines and offer a robust, auditable bridge between symbolic data and semantic music understanding."
}