English
Related papers

Related papers: Learning audio representations via phase predictio…

200 papers

The audio denoising technique has captured widespread attention in the deep neural network field. Recently, the audio denoising problem has been converted into an image generation task, and deep learning-based approaches have been applied…

Sound · Computer Science 2024-06-14 Junhui Li , Pu Wang , Jialu Li , Youshan Zhang

We propose a semi-supervised singing synthesizer, which is able to learn new voices from audio data only, without any annotations such as phonetic segmentation. Our system is an encoder-decoder model with two encoders, linguistic and…

Sound · Computer Science 2020-11-06 Jordi Bonada , Merlijn Blaauw

The research community has witnessed the powerful potential of self-supervised Masked Image Modeling (MIM), which enables the models capable of learning visual representation from unlabeled data. In this paper, to incorporate both the…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Wenxuan Wang , Jing Wang , Chen Chen , Jianbo Jiao , Yuanxiu Cai , Shanshan Song , Jiangyun Li

Bandwidth extension, the task of reconstructing the high-frequency components of an audio signal from its low-pass counterpart, is a long-standing problem in audio processing. While traditional approaches have evolved alongside the broader…

Sound · Computer Science 2025-11-27 Benoît Giniès , Xiaoyu Bie , Olivier Fercoq , Gaël Richard

Multilayer perceptrons (MLPs) learn high frequencies slowly. Recent approaches encode features in spatial bins to improve speed of learning details, but at the cost of larger model size and loss of continuity. Instead, we propose to encode…

Computer Vision and Pattern Recognition · Computer Science 2022-12-05 Jae Yong Lee , Yuqun Wu , Chuhang Zou , Shenlong Wang , Derek Hoiem

Transfer learning is critical for efficient information transfer across multiple related learning problems. A simple, yet effective transfer learning approach utilizes deep neural networks trained on a large-scale task for feature…

Sound · Computer Science 2021-06-23 Anurag Kumar , Yun Wang , Vamsi Krishna Ithapu , Christian Fuegen

This report will explore and answer fundamental questions about taking Fourier Transforms and tying it with recent advances in AI and neural architecture. One interpretation of the Fourier Transform is decomposing a signal into its…

Sound · Computer Science 2023-08-22 Prateek Verma

This thesis focuses on representation learning for sequence data over time or space, aiming to improve downstream sequence prediction tasks by using the learned representations. Supervised learning has been the most dominant approach for…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-02 Qingming Tang

We study the use of a time series encoder to learn representations that are useful on data set types with which it has not been trained on. The encoder is formed of a convolutional neural network whose temporal output is summarized by a…

Machine Learning · Computer Science 2018-05-11 Joan Serrà , Santiago Pascual , Alexandros Karatzoglou

Transformer architectures show spectacular performance on NLP tasks and have recently also been used for tasks such as image completion or image classification. Here we propose to use a sequential image representation, where each prefix of…

Computer Vision and Pattern Recognition · Computer Science 2022-04-20 Tim-Oliver Buchholz , Florian Jug

We propose an audio-to-audio neural network model that learns to denoise old music recordings. Our model internally converts its input into a time-frequency representation by means of a short-time Fourier transform (STFT), and processes the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-17 Yunpeng Li , Beat Gfeller , Marco Tagliasacchi , Dominik Roblek

Pre-trained models are essential as feature extractors in modern machine learning systems in various domains. In this study, we hypothesize that representations effective for general audio tasks should provide multiple aspects of robust…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-24 Daisuke Niizumi , Daiki Takeuchi , Yasunori Ohishi , Noboru Harada , Kunio Kashino

We present a representation learning method that learns features at multiple different levels of scale. Working within the unsupervised framework of denoising autoencoders, we observe that when the input is heavily corrupted during…

Machine Learning · Computer Science 2015-04-14 Krzysztof J. Geras , Charles Sutton

We present a novel neural encoder system for acoustic-to-articulatory inversion. We leverage the Pink Trombone voice synthesizer that reveals articulatory parameters (e.g tongue position and vocal cord configuration). Our system is designed…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-21 Mateo Cámara , Fernando Marcos , José Luis Blanco

Phase retrieval is the nonlinear inverse problem of recovering a true signal from its Fourier magnitude measurements. It arises in many applications such as astronomical imaging, X-Ray crystallography, microscopy, and more. The problem is…

Computer Vision and Pattern Recognition · Computer Science 2023-05-11 Rohun Agrawal , Oscar Leong

Representation learning is all about discovering the hidden modular attributes that generate the data faithfully. We explore the potential of Denoising Diffusion Probabilistic Model (DM) in unsupervised learning of the modular attributes.…

Computer Vision and Pattern Recognition · Computer Science 2024-01-23 Zhongqi Yue , Jiankun Wang , Qianru Sun , Lei Ji , Eric I-Chao Chang , Hanwang Zhang

Equivariant neural networks, whose hidden features transform according to representations of a group G acting on the data, exhibit training efficiency and an improved generalisation performance. In this work, we extend group invariant and…

Machine Learning · Computer Science 2024-04-15 Robin Winter , Marco Bertolini , Tuan Le , Frank Noé , Djork-Arné Clevert

We consider audio decoding as an inverse problem and solve it through diffusion posterior sampling. Explicit conditioning functions are developed for input signal measurements provided by an example of a transform domain perceptual audio…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-13 Pedro J. Villasana T. , Lars Villemoes , Janusz Klejsa , Per Hedelin

We capitalize on large amounts of readily-available, synchronous data to learn a deep discriminative representations shared across three major natural modalities: vision, sound and language. By leveraging over a year of sound from video and…

Computer Vision and Pattern Recognition · Computer Science 2017-06-06 Yusuf Aytar , Carl Vondrick , Antonio Torralba

This paper presents a novel phase reconstruction method (only from a given amplitude spectrogram) by combining a signal-processing-based approach and a deep neural network (DNN). To retrieve a time-domain signal from its amplitude…

Sound · Computer Science 2019-03-12 Yoshiki Masuyama , Kohei Yatabe , Yuma Koizumi , Yasuhiro Oikawa , Noboru Harada