SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.03929 · ICML · 2026

PHALAR: Phasors for Learned Musical Audio Representations

Emanuele Rodolà, Michele Mancusi, Donato Crisostomi, Giorgio Strano, Davide Marincione, Luca Cerovaz, Roberto Ribuoli

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
gladia-research-group/phalar canonical 2 of 3
FunctionStatusWhere it lives
complex_normalize Ran gladia-research-group/phalar/contrastive_model/similarity_ops.py
code served (permissive licence) · get_code("aa89ee116e16d0f3")
make_pre_pool_projector Ran gladia-research-group/phalar/contrastive_model/contrastive_model.py
code served (permissive licence) · get_code("cbf9325555fcb0fa")
get_normalization_factor Not yet run gladia-research-group/phalar/wrappers/phalar_downstream_wrapper.py
code served (permissive licence) · get_code("852aebd5b555be31")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Stem retrieval, the task of matching missing stems to a given audio submix, is a key challenge currently limited by models that discard temporal information. We introduce PHALAR, a contrastive framework achieving a relative accuracy increase of up to ≈ 70% over the state-of-the-art while requiring < 50% of the parameters and a 7× training speedup. By utilizing a Learned Spectral Pooling layer and a complex-valued head, PHALAR enforces pitch-equivariant and phase-equivariant biases. PHALAR establishes new retrieval stateof-the-art across MoisesDB, Slakh, and Choco-Chorales, correlating significantly higher with human coherence judgment than semantic baselines. Finally, zero-shot beat tracking and linear chord probing confirm that PHALAR captures robust musical structures beyond the retrieval task.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2605.03929")
get_code_for_paper("2605.03929")
have("2605.03929")

Connect an agent — have() is free.