A Quantized Native Runtime for On-Device Semantic Audio Generation
Paper • 2607.08526 • Published • 3
AI & ML interests
None defined yet.
Papers
View all Papers
matteospanio
authored a
paper 6 days ago
matteospanio
submitted a
paper to Daily Papers 6 days ago
matteospanio
submitted a
paper to Daily Papers 8 days ago
matteospanio
authored a
paper 9 days ago
matteospanio
authored 3
papers 10 days ago
Can LLMs understand LilyPond? A benchmark for symbolic music generation and understanding
Paper • 2606.08722 • Published
Multimodal Dataset Normalization and Perceptual Validation for Music-Taste Correspondences
Paper • 2604.10632 • Published
TorchFX: A modern approach to Audio DSP with PyTorch and GPU acceleration
Paper • 2504.08624 • Published • 1
matteospanio
posted an update about 1 month ago
Post
7080
🎶 Released mule-torch — an unofficial PyTorch port of MULE (SF-NFNet-F0), SiriusXM/Pandora's music-audio embedding model (McCallum et al., ISMIR 2022).
No retraining: I re-implemented the architecture in pure PyTorch and transferred the original TensorFlow weights, then checked it layer by layer against the genuine TF pipeline.
✅ End-to-end clip-embedding cosine 0.9999999 vs the original
✅ ONNX backbone parity < 1e-6
✅ 62.35M params (paper: ~62.4M)
✅ Batched, GPU-native, ONNX-exportable — none of which the original
🤗 Weights: matteospanio/mule
💻 Code: https://github.com/matteospanio/mule-torch
📦 PyPI: https://pypi.org/project/mule-torch/
The fun bug: parity was perfect through every conv but the block output was anti-correlated (cos = −1). Cause: the learnable skip-init gains couldn't be mapped by layer name (Keras scrambles the order) — they had to be recovered from the graph.
⚠️ Unofficial, community port — not affiliated with or endorsed by the original authors. All credit to them; please cite the paper. Weights inherit CC-BY-NC-4.0.
No retraining: I re-implemented the architecture in pure PyTorch and transferred the original TensorFlow weights, then checked it layer by layer against the genuine TF pipeline.
✅ End-to-end clip-embedding cosine 0.9999999 vs the original
✅ ONNX backbone parity < 1e-6
✅ 62.35M params (paper: ~62.4M)
✅ Batched, GPU-native, ONNX-exportable — none of which the original
Analysis pipeline doespip install mule-torchfrom mule_torch import MuleModel
emb = MuleModel.from_pretrained()(waveform) # (B, T)@16kHz -> (B, 1728)🤗 Weights: matteospanio/mule
💻 Code: https://github.com/matteospanio/mule-torch
📦 PyPI: https://pypi.org/project/mule-torch/
The fun bug: parity was perfect through every conv but the block output was anti-correlated (cos = −1). Cause: the learnable skip-init gains couldn't be mapped by layer name (Keras scrambles the order) — they had to be recovered from the graph.
⚠️ Unofficial, community port — not affiliated with or endorsed by the original authors. All credit to them; please cite the paper. Weights inherit CC-BY-NC-4.0.
Simom0
submitted a
paper to Daily Papers 3 months ago
matteospanio
authored a
paper 3 months ago
matteospanio
submitted a
paper to Daily Papers 3 months ago
matteospanio
posted an update 4 months ago
Post
168
🎧 Help us evaluate AI-generated music across cultures
We are running a new online survey to collect data for a follow-up study on AI-generated music and sonic seasoning: the phenomenon where sound can influence the perception of taste.
This study builds on our previous work:
📄 Paper: A Multimodal Symphony: Integrating Taste and Sound through Generative AI (2503.02823)
🤗 Model release: csc-unipd/tasty-musicgen-small
In the previous study we introduced Tasty MusicGen, a model designed to generate music associated with taste descriptors, and showed that it can effectively produce music that evokes specific taste-related sensations.
With this new survey, we aim to expand the participant pool to create a more inclusive and cross-cultural evaluation, helping us understand how these musical cues are perceived across different linguistic and cultural backgrounds.
Participants will listen to short AI-generated music clips and evaluate the sensations they evoke.
⏱️ Takes about 10 minutes
👉 Participate here:
https://matteospanio.github.io/tasty-music-survey/
Your participation will help us better understand how generative music models interact with human perception across cultures. Thanks to everyone who participates or shares!
We are running a new online survey to collect data for a follow-up study on AI-generated music and sonic seasoning: the phenomenon where sound can influence the perception of taste.
This study builds on our previous work:
📄 Paper: A Multimodal Symphony: Integrating Taste and Sound through Generative AI (2503.02823)
🤗 Model release: csc-unipd/tasty-musicgen-small
In the previous study we introduced Tasty MusicGen, a model designed to generate music associated with taste descriptors, and showed that it can effectively produce music that evokes specific taste-related sensations.
With this new survey, we aim to expand the participant pool to create a more inclusive and cross-cultural evaluation, helping us understand how these musical cues are perceived across different linguistic and cultural backgrounds.
Participants will listen to short AI-generated music clips and evaluate the sensations they evoke.
⏱️ Takes about 10 minutes
👉 Participate here:
https://matteospanio.github.io/tasty-music-survey/
Your participation will help us better understand how generative music models interact with human perception across cultures. Thanks to everyone who participates or shares!
Aleste
authored a
paper 5 months ago
matteospanio
authored a
paper over 1 year ago
