English
Related papers

Related papers: Taming Audio VAEs via Target-KL Regularization

200 papers

We introduce an improved variational autoencoder (VAE) for text modeling with topic information explicitly modeled as a Dirichlet latent variable. By providing the proposed model topic awareness, it is more superior at reconstructing input…

Computation and Language · Computer Science 2018-11-02 Yijun Xiao , Tiancheng Zhao , William Yang Wang

Integrating audio comprehension and generation into large language models (LLMs) remains challenging due to the continuous nature of audio and the resulting high sampling rates. Here, we introduce a novel approach that combines Variational…

Audio and Speech Processing · Electrical Eng. & Systems 2025-03-31 Shivam Mehta , Nebojsa Jojic , Hannes Gamper

While hierarchical variational autoencoders (VAEs) have achieved great density estimation on image modeling tasks, samples from their prior tend to look less convincing than models with similar log-likelihood. We attribute this to learned…

Machine Learning · Computer Science 2022-10-20 Eric Luhman , Troy Luhman

Recent achievements in end-to-end deep learning have encouraged the exploration of tasks dealing with highly structured data with unified deep network models. Having such models for compressing audio signals has been challenging since it…

Machine Learning · Computer Science 2021-07-14 Daniela N. Rim , Inseon Jang , Heeyoul Choi

Advances in latent diffusion models (LDMs) have revolutionized high-resolution image generation, but the design space of the autoencoder that is central to these systems remains underexplored. In this paper, we introduce LiteVAE, a new…

Machine Learning · Computer Science 2025-01-22 Seyedmorteza Sadat , Jakob Buhmann , Derek Bradley , Otmar Hilliges , Romann M. Weber

Variational auto-encoders (VAEs) are deep generative latent variable models that can be used for learning the distribution of complex data. VAEs have been successfully used to learn a probabilistic prior over speech signals, which is then…

Sound · Computer Science 2020-12-18 Mostafa Sadeghi , Simon Leglaive , Xavier Alameda-PIneda , Laurent Girin , Radu Horaud

Variational Autoencoder (VAE) is widely used as a generative model to approximate a model's posterior on latent variables by combining the amortized variational inference and deep neural networks. However, when paired with strong…

Machine Learning · Computer Science 2020-06-02 Qile Zhu , Jianlin Su , Wei Bi , Xiaojiang Liu , Xiyao Ma , Xiaolin Li , Dapeng Wu

Audio generation has achieved remarkable progress with the advance of sophisticated generative models, such as diffusion models (DMs) and autoregressive (AR) models. However, due to the naturally significant sequence length of audio, the…

Sound · Computer Science 2024-12-18 Kai Qiu , Xiang Li , Hao Chen , Jie Sun , Jinglu Wang , Zhe Lin , Marios Savvides , Bhiksha Raj

Discrete audio representation, aka audio tokenization, has seen renewed interest driven by its potential to facilitate the application of text language modeling approaches in audio domain. To this end, various compression and…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-21 Krishna C. Puvvada , Nithin Rao Koluguri , Kunal Dhawan , Jagadeesh Balam , Boris Ginsburg

Diffusion autoencoders (DAEs) are typically formulated as a noise prediction model and trained with a linear-$\beta$ noise schedule that spends much of its sampling steps at high noise levels. Because high noise levels are associated with…

Computer Vision and Pattern Recognition · Computer Science 2025-05-01 Pramook Khungurn , Sukit Seripanitkarn , Phonphrm Thawatdamrongkit , Supasorn Suwajanakorn

Controllable timbre synthesis has been a subject of research for several decades, and deep neural networks have been the most successful in this area. Deep generative models such as Variational Autoencoders (VAEs) have the ability to…

Sound · Computer Science 2023-07-21 Anastasia Natsiou , Luca Longo , Sean O'Leary

Variational autoencoders (VAEs) face a notorious problem wherein the variational posterior often aligns closely with the prior, a phenomenon known as posterior collapse, which hinders the quality of representation learning. To mitigate this…

Machine Learning · Statistics 2023-10-25 Yuma Ichikawa , Koji Hukushima

This paper reviews the novel concept of controllable variational autoencoder (ControlVAE), discusses its parameter tuning to meet application needs, derives its key analytic properties, and offers useful extensions and applications.…

Machine Learning · Computer Science 2020-11-04 Huajie Shao , Zhisheng Xiao , Shuochao Yao , Aston Zhang , Shengzhong Liu , Tarek Abdelzaher

In recent years, image generation has shown a great leap in performance, where diffusion models play a central role. Although generating high-quality images, such models are mainly conditioned on textual descriptions. This begs the…

Sound · Computer Science 2023-05-23 Guy Yariv , Itai Gat , Lior Wolf , Yossi Adi , Idan Schwartz

The research in Deep Learning applications in sound and music computing have gathered an interest in the recent years; however, there is still a missing link between these new technologies and on how they can be incorporated into real-world…

Sound · Computer Science 2023-06-21 Kıvanç Tatar , Kelsey Cotton , Daniel Bisig

Tokenizers are a crucial component of latent diffusion models, as they define the latent space in which diffusion models operate. However, existing tokenizers are primarily designed to improve reconstruction fidelity or inherit pretrained…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Zhengrong Yue , Taihang Hu , Mengting Chen , Haiyu Zhang , Zihao Pan , Tao Liu , Zikang Wang , Jinsong Lan , Xiaoyong Zhu , Bo Zheng , Yali Wang

Text-to-audio (TTA) generation is a recent popular problem that aims to synthesize general audio given text descriptions. Previous methods utilized latent diffusion models to learn audio embedding in a latent space with text embedding as…

Computer Vision and Pattern Recognition · Computer Science 2023-05-23 Shentong Mo , Jing Shi , Yapeng Tian

Most visual generative models compress images into a latent space before applying diffusion or autoregressive modelling. Yet, existing approaches such as VAEs and foundation model aligned encoders implicitly constrain the latent space…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Sen Ye , Jianning Pei , Mengde Xu , Shuyang Gu , Chunyu Wang , Liwei Wang , Han Hu

Large Audio Language Models (LALMs) demonstrate impressive performance across diverse tasks, ranging from speech recognition to general audio understanding. However, their scalability is limited by the quadratic complexity of attention and…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-27 Saurabhchand Bhati , Samuel Thomas , Hilde Kuehne , Rogerio Feris , James Glass

Latent diffusion models have emerged as the dominant framework for high-fidelity and efficient image generation, owing to their ability to learn diffusion processes in compact latent spaces. However, while previous research has focused…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Qifan Li , Xingyu Zhou , Jinhua Zhang , Weiyi You , Shuhang Gu