English
Related papers

Related papers: Learning Source Disentanglement in Neural Audio Co…

200 papers

We contribute an unsupervised method that effectively learns disentangled content and style representations from sequences of observations. Unlike most disentanglement algorithms that rely on domain-specific labels or knowledge, our method…

Machine Learning · Computer Science 2025-03-18 Yuxuan Wu , Ziyu Wang , Bhiksha Raj , Gus Xia

The state of the art in music source separation employs neural networks trained in a supervised fashion on multi-track databases to estimate the sources from a given mixture. With only few datasets available, often extensive data…

Machine Learning · Computer Science 2018-04-09 Daniel Stoller , Sebastian Ewert , Simon Dixon

Variational autoencoders (VAEs) are among leading approaches to address the problem of learning disentangled representations. Typically a single VAE is used and disentangled representations are sought within its single continuous latent…

Machine Learning · Statistics 2026-04-02 Veranika Boukun , Jörg Lücke

Sound-guided object segmentation has drawn considerable attention for its potential to enhance multimodal perception. Previous methods primarily focus on developing advanced architectures to facilitate effective audio-visual interactions,…

Sound · Computer Science 2025-03-18 Chen Liu , Liying Yang , Peike Li , Dadong Wang , Lincheng Li , Xin Yu

Audio source separation is the process of separating a mixture (e.g. a pop band recording) into isolated sounds from individual sources (e.g. just the lead vocals). Deep learning models are the state-of-the-art in source separation, given…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-28 Alisa Liu , Prem Seetharaman , Bryan Pardo

We introduce Audio-SDS, a generalization of Score Distillation Sampling (SDS) to text-conditioned audio diffusion models. While SDS was initially designed for text-to-3D generation using image diffusion, its core idea of distilling a…

Sound · Computer Science 2025-05-08 Jessie Richter-Powell , Antonio Torralba , Jonathan Lorraine

Deep learning techniques for separating audio into different sound sources face several challenges. Standard architectures require training separate models for different types of audio sources. Although some universal separators employ a…

Sound · Computer Science 2022-02-15 Ke Chen , Xingjian Du , Bilei Zhu , Zejun Ma , Taylor Berg-Kirkpatrick , Shlomo Dubnov

Cinematic audio source separation is a relatively new subtask of audio source separation, with the aim of extracting the dialogue, music, and effects stems from their mixture. In this work, we developed a model generalizing the Bandsplit…

Audio and Speech Processing · Electrical Eng. & Systems 2024-08-27 Karn N. Watcharasupat , Chih-Wei Wu , Yiwei Ding , Iroro Orife , Aaron J. Hipple , Phillip A. Williams , Scott Kramer , Alexander Lerch , William Wolcott

Representation learning focused on disentangling the underlying factors of variation in given data has become an important area of research in machine learning. However, most of the studies in this area have relied on datasets from the…

Machine Learning · Computer Science 2020-07-31 Ashis Pati , Siddharth Gururani , Alexander Lerch

With the rapid advancement of neural audio codecs, codec-based speech generation (CoSG) systems have become highly powerful. Unfortunately, CoSG also enables the creation of highly realistic deepfake speech, making it easier to mimic an…

Reasoning about spatial audio with large language models requires a spatial audio encoder as an acoustic front-end to obtain audio embeddings for further processing. Such an encoder needs to capture all information required to detect the…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-04 Kevin Wilkinghoff , Zheng-Hua Tan

Neural audio codec models are becoming increasingly important as they serve as tokenizers for audio, enabling efficient transmission or facilitating speech language modeling. The ideal neural audio codec should maintain content,…

Self-supervised learning in speech involves training a speech representation network on a large-scale unannotated speech corpus, and then applying the learned representations to downstream tasks. Since the majority of the downstream tasks…

Recent approaches for music source separation are almost exclusively based on deep neural networks, mostly employing recurrent neural networks (RNNs). Although RNNs are in many cases superior than other types of deep neural networks for…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-08 Pyry Pyykkönen , Styliannos I. Mimilakis , Konstantinos Drossos , Tuomas Virtanen

Deep convolutional neural networks are known to specialize in distilling compact and robust prior from a large amount of data. We are interested in applying deep networks in the absence of training dataset. In this paper, we introduce deep…

Sound · Computer Science 2019-12-24 Yapeng Tian , Chenliang Xu , Dingzeyu Li

Models for audio source separation usually operate on the magnitude spectrum, which ignores phase information and makes separation performance dependant on hyper-parameters for the spectral front-end. Therefore, we investigate end-to-end…

Sound · Computer Science 2018-06-11 Daniel Stoller , Sebastian Ewert , Simon Dixon

Neural compression offers a domain-agnostic approach to creating codecs for lossy or lossless compression via deep generative models. For sequence compression, however, most deep sequence models have costs that scale with the sequence…

Machine Learning · Computer Science 2022-12-29 Ricky T. Q. Chen , Matthew Le , Matthew Muckley , Maximilian Nickel , Karen Ullrich

Disentangled sequential autoencoders (DSAEs) represent a class of probabilistic graphical models that describes an observed sequence with dynamic latent variables and a static latent variable. The former encode information at a frame rate…

Sound · Computer Science 2022-06-16 Yin-Jyun Luo , Sebastian Ewert , Simon Dixon

Disentangling content and speaking style information is essential for zero-shot non-parallel voice conversion (VC). Our previous study investigated a novel framework with disentangled sequential variational autoencoder (DSVAE) as the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-22 Jiachen Lian , Chunlei Zhang , Gopala Krishna Anumanchipalli , Dong Yu

Convolutional layers with 1-D filters are often used as frontend to encode audio signals. Unlike fixed time-frequency representations, they can adapt to the local characteristics of input data. However, 1-D filters on raw audio are hard to…

Sound · Computer Science 2024-09-02 Daniel Haider , Felix Perfler , Vincent Lostanlen , Martin Ehler , Peter Balazs