English
Related papers

Related papers: Do Foundational Audio Encoders Understand Music St…

200 papers

Audio-based music structure analysis (MSA) is an essential task in Music Information Retrieval that remains challenging due to the complexity and variability of musical form. Recent advances highlight the potential of fine-tuning…

Sound · Computer Science 2025-07-21 Yixiao Zhang , Haonan Chen , Ju-Chiang Wang , Jitong Chen

Audio pretrained models are widely employed to solve various tasks in speech processing, sound event detection, or music information retrieval. However, the representations learned by these models are unclear, and their analysis mainly…

In this paper, we propose to pre-train audio encoders using synthetic patterns instead of real audio data. Our proposed framework consists of two key elements. The first one is Masked Autoencoder (MAE), a self-supervised learning framework…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-02 Yuchi Ishikawa , Tatsuya Komatsu , Yoshimitsu Aoki

Bioacoustic recognition requires fine-grained acoustic understanding to distinguish similar-sounding species. However, many large-scale data repositories such as iNaturalist are weakly annotated, often with only a single positive species…

Sound · Computer Science 2026-05-15 Wuao Liu , Mustafa Chasmai , Subhransu Maji , Grant Van Horn

Masked Autoencoders (MAEs) learn rich semantic representations in audio classification through an efficient self-supervised reconstruction task. However, general-purpose models fail to generalize well when applied directly to fine-grained…

Machine Learning · Computer Science 2025-08-20 Lukas Rauch , René Heinrich , Ilyass Moummad , Alexis Joly , Bernhard Sick , Christoph Scholz

Audio classification and restoration are among major downstream tasks in audio signal processing. However, restoration derives less of a benefit from pretrained models compared to the overwhelming success of pretrained models in…

Music structure analysis (MSA) methods traditionally search for musically meaningful patterns in audio: homogeneity, repetition, novelty, and segment-length regularity. Hand-crafted audio features such as MFCCs or chromagrams are often used…

Audio and Speech Processing · Electrical Eng. & Systems 2022-05-03 Ju-Chiang Wang , Jordan B. L. Smith , Wei-Tsung Lu , Xuchen Song

This paper studies a simple extension of image-based Masked Autoencoders (MAE) to self-supervised representation learning from audio spectrograms. Following the Transformer encoder-decoder design in MAE, our Audio-MAE first encodes audio…

Recent general-purpose audio representations show state-of-the-art performance on various audio tasks. These representations are pre-trained by self-supervised learning methods that create training signals from the input. For example,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-09 Daisuke Niizumi , Daiki Takeuchi , Yasunori Ohishi , Noboru Harada , Kunio Kashino

Music Structure Analysis (MSA) consists in segmenting a music piece in several distinct sections. We approach MSA within a compression framework, under the hypothesis that the structure is more easily revealed by a simplified representation…

Sound · Computer Science 2022-04-18 Axel Marmoret , Jérémy E. Cohen , Frédéric Bimbot

Music Structure Analysis (MSA) aims to uncover the high-level organization of musical pieces. State-of-the-art methods are often based on supervised deep learning, but these methods are bottlenecked by the need for heavily annotated data…

Sound · Computer Science 2026-03-31 Axel Marmoret

We investigated the adaptation and performance of Masked Autoencoders (MAEs) with Vision Transformer (ViT) architectures for self-supervised representation learning on one-dimensional (1D) ultrasound signals. Although MAEs have demonstrated…

Machine Learning · Computer Science 2025-08-29 Immanuel Roßteutscher , Klaus S. Drese , Thorsten Uphues

Sparse Autoencoders (SAEs) are powerful tools for interpreting neural representations, yet their use in audio remains underexplored. We train SAEs across all encoder layers of Whisper and HuBERT, provide an extensive evaluation of their…

Masked AutoEncoders (MAE) have emerged as a robust self-supervised framework, offering remarkable performance across a wide range of downstream tasks. To increase the difficulty of the pretext task and learn richer visual representations,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Carlos Hinojosa , Shuming Liu , Bernard Ghanem

Self-supervised learning has been a powerful training paradigm to facilitate representation learning. In this study, we design a masked autoencoder (MAE) to guide deep learning models to learn electroencephalography (EEG) signal…

Human-Computer Interaction · Computer Science 2024-09-04 Yifei Zhou , Sitong Liu

Masked Autoencoders (MAEs) trained on audio spectrogram patches have emerged as a prominent approach for learning self-supervised audio representations. While several recent papers have evaluated key aspects of training MAEs on audio data,…

Sound · Computer Science 2025-07-15 Sarthak Yadav , Sergios Theodoridis , Zheng-Hua Tan

Self-supervised audio representation learning offers an attractive alternative for obtaining generic audio embeddings, capable to be employed into various downstream tasks. Published approaches that consider both audio and words/tags…

Sound · Computer Science 2020-10-28 Xavier Favory , Konstantinos Drossos , Tuomas Virtanen , Xavier Serra

The complex nature of musical emotion introduces inherent bias in both recognition and generation, particularly when relying on a single audio encoder, emotion classifier, or evaluation metric. In this work, we conduct a study on Music…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-01 Yuanchao Li , Azalea Gui , Dimitra Emmanouilidou , Hannes Gamper

Ultrasound imaging is one of the most widely used diagnostic modalities, offering real-time, radiation-free assessment across diverse clinical domains. However, interpretation of ultrasound images remains challenging due to high noise…

Image and Video Processing · Electrical Eng. & Systems 2025-11-10 Youssef Megahed , Robin Ducharme , Aylin Erman , Mark Walker , Steven Hawken , Adrian D. C. Chan

Over the years, Music Information Retrieval (MIR) research community has released various models pretrained on large amounts of music data. Transfer learning showcases the proven effectiveness of pretrained backend models for a broad…

Information Retrieval · Computer Science 2026-04-28 Yan-Martin Tamm , Anna Aljanaki
‹ Prev 1 2 3 10 Next ›