I can listen but cannot read: An evaluation of two-tower multimodal systems for instrument recognition
July 25, 2024 ยท Declared Dead ยท ๐ International Society for Music Information Retrieval Conference
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Yannis Vasilakis, Rachel Bittner, Johan Pauwels
arXiv ID
2407.18058
Category
cs.SD: Sound
Cross-listed
cs.CL,
cs.IR,
cs.LG,
eess.AS
Citations
5
Venue
International Society for Music Information Retrieval Conference
Last Checked
3 months ago
Abstract
Music two-tower multimodal systems integrate audio and text modalities into a joint audio-text space, enabling direct comparison between songs and their corresponding labels. These systems enable new approaches for classification and retrieval, leveraging both modalities. Despite the promising results they have shown for zero-shot classification and retrieval tasks, closer inspection of the embeddings is needed. This paper evaluates the inherent zero-shot properties of joint audio-text spaces for the case-study of instrument recognition. We present an evaluation and analysis of two-tower systems for zero-shot instrument recognition and a detailed analysis of the properties of the pre-joint and joint embeddings spaces. Our findings suggest that audio encoders alone demonstrate good quality, while challenges remain within the text encoder or joint space projection. Specifically, two-tower systems exhibit sensitivity towards specific words, favoring generic prompts over musically informed ones. Despite the large size of textual encoders, they do not yet leverage additional textual context or infer instruments accurately from their descriptions. Lastly, a novel approach for quantifying the semantic meaningfulness of the textual space leveraging an instrument ontology is proposed. This method reveals deficiencies in the systems' understanding of instruments and provides evidence of the need for fine-tuning text encoders on musical data.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Sound
๐ฎ
๐ฎ
The Ethereal
R.I.P.
๐ป
Ghosted
Multi-talker Speech Separation with Utterance-level Permutation Invariant Training of Deep Recurrent Neural Networks
R.I.P.
๐ป
Ghosted
The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines
R.I.P.
๐ป
Ghosted
TasNet: time-domain audio separation network for real-time, single-channel speech separation
R.I.P.
๐ป
Ghosted
SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
R.I.P.
๐ป
Ghosted
MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation
Died the same way โ ๐ป Ghosted
R.I.P.
๐ป
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
๐ป
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
๐ป
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
๐ป
Ghosted