English
Related papers

Related papers: Efficient Supervised Training of Audio Transformer…

200 papers

The great success of transformer-based models in natural language processing (NLP) has led to various attempts at adapting these architectures to other domains such as vision and audio. Recent work has shown that transformers can outperform…

Sound · Computer Science 2023-01-26 Khaled Koutini , Jan Schlüter , Hamid Eghbal-zadeh , Gerhard Widmer

The success of supervised deep learning methods is largely due to their ability to learn relevant features from raw data. Deep Neural Networks (DNNs) trained on large-scale datasets are capable of capturing a diverse set of features, and…

Transformer-based models attain excellent results and generalize well when trained on sufficient amounts of data. However, constrained by the limited data available in the audio domain, most transformer-based models for audio tasks are…

Sound · Computer Science 2022-04-28 Dading Chong , Helin Wang , Peilin Zhou , Qingcheng Zeng

In this paper, we propose a simple yet powerful improvement over the recent Self-Supervised Audio Spectrogram Transformer (SSAST) model for speech and audio classification. Specifically, we leverage the insight that the SSAST uses a very…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-01 Alan Baade , Puyuan Peng , David Harwath

Recently, neural networks based purely on self-attention, such as the Vision Transformer (ViT), have been shown to outperform deep learning models constructed with convolutional neural networks (CNNs) on various vision tasks, thus extending…

Sound · Computer Science 2022-02-14 Yuan Gong , Cheng-I Jeff Lai , Yu-An Chung , James Glass

We present Music Tagging Transformer that is trained with a semi-supervised approach. The proposed model captures local acoustic characteristics in shallow convolutional layers, then temporally summarizes the sequence of the extracted…

Sound · Computer Science 2021-11-29 Minz Won , Keunwoo Choi , Xavier Serra

In this work, we provide a broad comparative analysis of strategies for pre-training audio understanding models for several tasks in the music domain, including labelling of genre, era, origin, mood, instrumentation, key, pitch, vocal…

We study the usability of pre-trained weakly supervised audio tagging (AT) models as feature extractors for general audio representations. We mainly analyze the feasibility of transferring those embeddings to other tasks within the speech…

Sound · Computer Science 2022-10-03 Heinrich Dinkel , Zhiyong Yan , Yongqing Wang , Junbo Zhang , Yujun Wang

Self-supervised pre-training using so-called "pretext" tasks has recently shown impressive performance across a wide range of modalities. In this work, we advance self-supervised learning from permutations, by pre-training a model to…

Sound · Computer Science 2021-05-05 Andrew N Carr , Quentin Berthet , Mathieu Blondel , Olivier Teboul , Neil Zeghidour

Recently, a variety of acoustic tasks and related applications arised. For many acoustic tasks, the labeled data size may be limited. To handle this problem, we propose an unsupervised pre-training method using Transformer based encoder to…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-09 Ruixiong Zhang , Haiwei Wu , Wubo Li , Dongwei Jiang , Wei Zou , Xiangang Li

Self-supervised learning has emerged as a powerful way to pre-train generalizable machine learning models on large amounts of unlabeled data. It is particularly compelling in the music domain, where obtaining labeled data is time-consuming,…

Sound · Computer Science 2024-04-16 Gabriel Meseguer-Brocal , Dorian Desblancs , Romain Hennequin

Transformer-based audio self-supervised learning (SSL) models commonly use spectrograms, vision-style Transformers, and masked modeling objectives. However, convolutional patchification with temporal downsampling lowers the effective…

Sound · Computer Science 2026-05-15 Kohei Yamamoto , Kosuke Okusa

Deep learning is very data hungry, and supervised learning especially requires massive labeled data to work well. Machine listening research often suffers from limited labeled data problem, as human annotations are costly to acquire, and…

Sound · Computer Science 2021-02-08 Ho-Hsiang Wu , Chieh-Chi Kao , Qingming Tang , Ming Sun , Brian McFee , Juan Pablo Bello , Chao Wang

Parameter-efficient transfer learning (PETL) methods have emerged as a solid alternative to the standard full fine-tuning approach. They only train a few extra parameters for each downstream task, without sacrificing performance and…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-16 Umberto Cappellazzo , Daniele Falavigna , Alessio Brutti , Mirco Ravanelli

Transformers have become central to recent advances in audio classification. However, training an audio spectrogram transformer, e.g. AST, from scratch can be resource and time-intensive. Furthermore, the complexity of transformers heavily…

Sound · Computer Science 2024-01-17 Jiu Feng , Mehmet Hamza Erol , Joon Son Chung , Arda Senocak

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

While the transformer has emerged as the eminent neural architecture, several independent lines of research have emerged to address its limitations. Recurrent neural approaches have observed a lot of renewed interest, including the extended…

Sound · Computer Science 2025-08-20 Sarthak Yadav , Sergios Theodoridis , Zheng-Hua Tan

We propose an efficient approach to train large diffusion models with masked transformers. While masked transformers have been extensively explored for representation learning, their application to generative learning is less explored in…

Computer Vision and Pattern Recognition · Computer Science 2024-03-06 Hongkai Zheng , Weili Nie , Arash Vahdat , Anima Anandkumar

Transformers have rapidly overtaken CNN-based architectures as the new standard in audio classification. Transformer-based models, such as the Audio Spectrogram Transformers (AST), also inherit the fixed-size input paradigm from CNNs.…

Sound · Computer Science 2024-07-12 Jiu Feng , Mehmet Hamza Erol , Joon Son Chung , Arda Senocak

Recent foundational models, SSAST, EAT, HuBERT, Qwen-Audio, and Audio Flamingo, achieve top-tier results across standard audio benchmarks but are limited by fixed input rates and durations, hindering their reusability. This paper introduces…

Sound · Computer Science 2025-11-25 Weichuang Shao , Iman Yi Liao , Tomas Henrique Bode Maul , Tissa Chandesa
‹ Prev 1 2 3 10 Next ›