English
Related papers

Related papers: Generative timbre spaces: regularizing variational…

200 papers

Voice conversion models modify timbre while preserving paralinguistic features, enabling applications like dubbing and identity protection. However, most VC systems require access to target utterances, limiting their use when target data is…

Sound · Computer Science 2025-11-11 Meiying Melissa Chen , Zhenyu Wang , Zhiyao Duan

Variational autoencoders (VAEs) are a popular class of deep generative models with many variants and a wide range of applications. Improvements upon the standard VAE mostly focus on the modelling of the posterior distribution over the…

Machine Learning · Computer Science 2022-11-02 James Langley , Miguel Monteiro , Charles Jones , Nick Pawlowski , Ben Glocker

Deep learning models need a sufficient amount of data in order to be able to find the hidden patterns in it. It is the purpose of generative modeling to learn the data distribution, thus allowing us to sample more data and augment the…

Machine Learning · Computer Science 2024-11-28 José Fernando Núñez , Jamie Arjona , Javier Béjar

Generative deep neural networks used in machine learning, like the Variational Auto-Encoders (VAE), and Generative Adversarial Networks (GANs) produce new objects each time when asked to do so with the constraint that the new objects remain…

Machine Learning · Statistics 2023-03-15 Gabriel Turinici

Variational Autoencoders (VAEs) are essential for large-scale audio tasks like diffusion-based generation. However, existing open-source models often neglect auditory perceptual aspects during training, leading to weaknesses in phase…

Sound · Computer Science 2025-11-07 Kangdi Wang , Zhiyue Wu , Dinghao Zhou , Rui Lin , Junyu Dai , Tao Jiang

Structuring the latent space in probabilistic deep generative models, e.g., variational autoencoders (VAEs), is important to yield more expressive models and interpretable representations, and to avoid overfitting. One way to achieve this…

Machine Learning · Computer Science 2022-06-20 Mostafa Sadeghi , Paul Magron

This paper focuses on explaining the timbre conveyed by speech signals and introduces a task termed voice timbre attribute detection (vTAD). In this task, voice timbre is explained with a set of sensory attributes describing its human…

Sound · Computer Science 2025-06-24 Jinghao He , Zhengyan Sheng , Liping Chen , Kong Aik Lee , Zhen-Hua Ling

The Synesthetic Variational Autoencoder (SynVAE) introduced in this research is able to learn a consistent mapping between visual and auditive sensory modalities in the absence of paired datasets. A quantitative evaluation on MNIST as well…

Computer Vision and Pattern Recognition · Computer Science 2019-09-15 Maximilian Müller-Eberstein , Nanne van Noord

By pretraining to synthesize coherent images from perturbed inputs, generative models inherently learn to understand object boundaries and scene compositions. How can we repurpose these generative representations for general-purpose…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Om Khangaonkar , Hamed Pirsiavash

Good generative models should not only synthesize high quality data, but also utilize interpretable representations that aid human understanding of their behavior. However, it is difficult to measure objectively if and to what degree…

Machine Learning · Computer Science 2025-04-09 Daniel Galperin , Ullrich Köthe

Continuous speech representations based on Variational Autoencoders (VAEs) have emerged as a promising alternative to traditional spectrogram or discrete token based features for speech generation and reconstruction. Recent research has…

Sound · Computer Science 2026-05-26 Changhao Cheng , Wei Wang , Wangyou Zhang , Dongya Jia , Jian Wu , Zhuo Chen , Yanmin Qian

Vector Quantized Variational Autoencoders (VQ-VAEs) are fundamental to modern generative modeling, yet they often suffer from training instability and "codebook collapse" due to the inherent coupling of representation learning and discrete…

Machine Learning · Computer Science 2026-02-20 Linwei Zhai , Han Ding , Mingzhi Lin , Cui Zhao , Fei Wang , Ge Wang , Wang Zhi , Wei Xi

With the advent of data-driven statistical modeling and abundant computing power, researchers are turning increasingly to deep learning for audio synthesis. These methods try to model audio signals directly in the time or frequency domain.…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-13 Krishna Subramani , Preeti Rao , Alexandre D'Hooge

Variational autoencoders (VAEs) have been used extensively to discover low-dimensional latent factors governing neural activity and animal behavior. However, without careful model selection, the uncovered latent factors may reflect noise in…

Machine Learning · Computer Science 2023-12-13 Julia Huiming Wang , Dexter Tsin , Tatiana Engel

It is increasingly considered that human speech perception and production both rely on articulatory representations. In this paper, we investigate whether this type of representation could improve the performances of a deep generative model…

Sound · Computer Science 2021-04-08 Marc-Antoine Georges , Laurent Girin , Jean-Luc Schwartz , Thomas Hueber

Music is a mysterious language that conveys feeling and thoughts via different tones and timbre. For better understanding of timbre in music, we chose music data of 6 representative instruments, analysed their timbre features and classified…

Sound · Computer Science 2022-07-15 Zishuo Zhao , Haoyun Wang

Large climate-model ensembles are computationally expensive; yet many downstream analyses would benefit from additional, statistically consistent realizations of spatiotemporal climate variables. We study a generative modeling approach for…

Machine Learning · Computer Science 2026-01-06 Jacquelyn Shelton , Przemyslaw Polewski , Alexander Robel , Matthew Hoffman , Stephen Price

In recent years, research on music transcription has focused mainly on architecture design and instrument-specific data acquisition. With the lack of availability of diverse datasets, progress is often limited to solo-instrument tasks such…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-25 Frank Cwitkowitz , Kin Wai Cheuk , Woosung Choi , Marco A. Martínez-Ramírez , Keisuke Toyama , Wei-Hsiang Liao , Yuki Mitsufuji

Traditional acoustic environment classification relies on: i) classical signal processing algorithms, which are unable to extract meaningful representations of high-dimensional data; or on ii) supervised learning, limited by the…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-22 Luan Vinícius Fiorio , Ivana Nikoloska , Wim van Houtum , Ronald M. Aarts

While many text-to-audio systems produce monophonic or fixed-stereo outputs, generating audio with user-defined spatial properties remains a challenge. Existing deep learning-based spatialization methods often rely on latent-space…

Sound · Computer Science 2025-09-16 Tutti Chi , Letian Gao , Yixiao Zhang