English
Related papers

Related papers: Do Foundational Audio Encoders Understand Music St…

200 papers

Sparse autoencoders (SAEs) have been used widely to decompose and interpret neural network activations, especially those of transformer language models. One key issue with SAEs is their inability to directly model multidimensional features.…

Machine Learning · Computer Science 2026-05-12 Collin Francel

The lack of data tends to limit the outcomes of deep learning research, particularly when dealing with end-to-end learning stacks processing raw data such as waveforms. In this study, 1.2M tracks annotated with musical labels are available…

Sound · Computer Science 2018-06-18 Jordi Pons , Oriol Nieto , Matthew Prockup , Erik Schmidt , Andreas Ehmann , Xavier Serra

Modeling of music audio semantics has been previously tackled through learning of mappings from audio data to high-level tags or latent unsupervised spaces. The resulting semantic spaces are theoretically limited, either because the chosen…

Information Retrieval · Computer Science 2017-12-18 Francisco Raposo , David Martins de Matos , Ricardo Ribeiro , Suhua Tang , Yi Yu

Autoencoders have been used for finding interpretable and disentangled features underlying neural network representations in both image and text domains. While the efficacy and pitfalls of such methods are well-studied in vision, there is a…

Machine Learning · Computer Science 2025-02-06 Abhinav Menon , Manish Shrivastava , David Krueger , Ekdeep Singh Lubana

Recent advancements in foundation models have significantly impacted various fields, including natural language processing, computer vision, and multi-modal tasks. One area that stands to benefit greatly is Earth observation, where these…

Computer Vision and Pattern Recognition · Computer Science 2024-10-21 Yohei Nakayama , Jiawei Su , Luis M. Pazos-Outón

The research in Deep Learning applications in sound and music computing have gathered an interest in the recent years; however, there is still a missing link between these new technologies and on how they can be incorporated into real-world…

Sound · Computer Science 2023-06-21 Kıvanç Tatar , Kelsey Cotton , Daniel Bisig

Music annotation has always been one of the critical topics in the field of Music Information Retrieval (MIR). Traditional models use supervised learning for music annotation tasks. However, as supervised machine learning approaches…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-02 Yilun Zhao , Jia Guo

This paper investigates foundation models tailored for music informatics, a domain currently challenged by the scarcity of labeled data and generalization issues. To this end, we conduct an in-depth comparative study among various…

Sound · Computer Science 2023-11-07 Minz Won , Yun-Ning Hung , Duc Le

Sparse autoencoders (SAEs) are a popular method for interpreting concepts represented in large language model (LLM) activations. However, there is a lack of evidence regarding the validity of their interpretations due to the lack of a…

Machine Learning · Computer Science 2025-02-25 Subhash Kantamneni , Joshua Engels , Senthooran Rajamanoharan , Max Tegmark , Neel Nanda

Masked Autoencoders (MAEs) achieve impressive performance in image classification tasks, yet the internal representations they learn remain less understood. This work started as an attempt to understand the strong downstream classification…

Machine Learning · Computer Science 2026-02-04 Anika Shrivastava , Renu Rameshan , Samar Agnihotri

Foundational models (FMs), pretrained on extensive datasets using self-supervised techniques, are capable of learning generalized patterns from large amounts of data. This reduces the need for extensive labeled datasets for each new task,…

Machine Learning · Computer Science 2024-06-19 Quan M. Tran , Suong N. Hoang , Lam M. Nguyen , Dzung Phan , Hoang Thanh Lam

Masked Autoencoders (MAE) have been popular paradigms for large-scale vision representation pre-training. However, MAE solely reconstructs the low-level RGB signals after the decoder and lacks supervision upon high-level semantics for the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-10 Peng Gao , Renrui Zhang , Rongyao Fang , Ziyi Lin , Hongyang Li , Hongsheng Li , Qiao Yu

Masked Autoencoders (MAEs) learn rich low-level representations from unlabeled data but require substantial labeled data to effectively adapt to downstream tasks. Conversely, Instance Discrimination (ID) emphasizes high-level semantics,…

Sound · Computer Science 2024-03-15 Afrina Tabassum , Dung Tran , Trung Dang , Ismini Lourentzou , Kazuhito Koishida

Cross-modal retrieval is to utilize one modality as a query to retrieve data from another modality, which has become a popular topic in information retrieval, machine learning, and database. How to effectively measure the similarity between…

Information Retrieval · Computer Science 2021-12-07 Jiwei Zhang , Yi Yu , Suhua Tang , Jianming Wu , Wei Li

The goal of this work is to investigate what singing voice separation approaches based on neural networks learn from the data. We examine the mapping functions of neural networks based on the denoising autoencoder (DAE) model that are…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-22 Stylianos Ioannis Mimilakis , Konstantinos Drossos , Estefanía Cano , Gerald Schuller

Partial audio deepfakes, where synthesized segments are spliced into genuine recordings, are particularly deceptive because most of the audio remains authentic. Existing detectors are supervised: they require frame-level annotations,…

Sound · Computer Science 2026-04-02 Awais Khan , Muhammad Umar Farooq , Kutub Uddin , Khalid Malik

Speech signal is constituted and contributed by various informative factors, such as linguistic content and speaker characteristic. There have been notable recent studies attempting to factorize speech signal into these individual factors…

Audio and Speech Processing · Electrical Eng. & Systems 2019-11-06 Zhiyuan Peng , Siyuan Feng , Tan Lee

We propose transfer learning as a method for analyzing the encoding of grammatical structure in neural language models. We train LSTMs on non-linguistic data and evaluate their performance on natural language to assess which kinds of data…

Computation and Language · Computer Science 2020-11-02 Isabel Papadimitriou , Dan Jurafsky

"Masked Autoencoders (MAE) Are Scalable Vision Learners" revolutionizes the self-supervised learning method in that it not only achieves the state-of-the-art for image pre-training, but is also a milestone that bridges the gap between…

Computer Vision and Pattern Recognition · Computer Science 2022-02-10 Shuhao Cao , Peng Xu , David A. Clifton

Masked Autoencoder (MAE) has recently been shown to be effective in pre-training Vision Transformers (ViT) for natural image analysis. By reconstructing full images from partially masked inputs, a ViT encoder aggregates contextual…

Image and Video Processing · Electrical Eng. & Systems 2023-04-24 Lei Zhou , Huidong Liu , Joseph Bae , Junjun He , Dimitris Samaras , Prateek Prasanna