Papers for

music recommendation engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Hidden neurons in audio classifiers linked to meaningful sound concepts

Bridging Neural Representations and Symbolic Semantics in Audio Classification

Abstract: Deep audio classifiers can achieve strong predictive performance, but their hidden representations remain difficult to interpret. Existing audio explainability methods often focus on input-level attribution, such as waveform segments, spectrogram regions, or acoustic features, and provide limited insight into what hidden neurons encode. Interpreting hidden neurons at the concept level can provide a more meaningful view of what an audio model learns internally. This paper investigates whether hidden neurons in audio classifiers can be associated with human-understandable symbolic acoustic concepts. A model-agnostic neurosymbolic framework is presented for analyzing the final hidden layer of audio classifiers, containing 32 neurons, through symbolic concept induction. The framework is evaluated on two audio classification settings: music genre classification using GTZAN dataset and musical instrument classification using IRMAS dataset. Results show that several hidden neurons can be associated with meaningful induced concepts, and most confirmed neuron-concept pairs are statistically supported using the Mann-Whitney U test. These findings suggest that symbolic concept induction is a promising direction for explaining latent audio representations beyond input-level attribution.

Thu 29 OctSoundArtificial Intelligence
The gist
Deep learning models that identify sounds do a good job but often work like black boxes that are hard to understand. The authors studied whether the neurons inside these models represent simple, understandable sound concepts like musical instruments or genres. They developed a framework that connects the neurons to symbolic concepts and tested it on music datasets. Their results show that many neurons do correspond to meaningful concepts, helping explain what the model learns beyond just looking at the sound input.
Open → 2610.40414v1

Text to music models improved with rubric based optimization

Rubric-Based Optimization for Text-to-Music Generation

Abstract: Post-training text-to-music generation requires reward signals that capture multiple aspects of musical quality beyond what any single automatic metric can measure. We study structured, rubric-based rewards from pretrained audio-language models (ALMs) as training signals for both autoregressive and diffusion-based music generators. An ALM scores each generated clip against the rubric; we rank candidates generated for the same text prompt by their scores and convert these rankings into preference pairs for DPO on both MusicGen-small and ACE-Step~v1, and additionally use the rubric scores directly as scalar rewards for DiffusionNFT on ACE-Step~v1. On MusicCaps, rubric-based optimization improves CLAP, SongEval, and Audiobox-Aesthetics simultaneously, with the strongest gains obtained by DiffusionNFT on ACE-Step. By contrast, on MusicGen-small, building preferences from any one of these automatic evaluators produces clear cross-metric trade-offs: the targeted evaluator improves while other independent evaluators deteriorate. We further study tempo, key, and instrumentation, where precise objective rewards are available. Directly optimizing these specialized rewards reliably improves the target attributes, whereas ALM rubrics provide only partial transfer for tempo and instrumentation and no measurable improvement for key. Together, these results suggest a practical division of labor: ALM rubrics are effective for broad perceptual qualities that are difficult to formalize, while specialized objective rewards remain preferable when reliable measurements are available.

Fri 2 OctSound
The gist
Generating music from text is hard because it's difficult to measure what makes music good. The authors study using detailed scorecards, called rubrics, from special audio-language models to judge music quality during training. They find that these rubric scores help improve musical qualities that are tricky to define, but for specific features like tempo or key, direct measurements work better. This approach helps train music generators that produce more pleasing music in several ways.
Open → 2610.03589v1