English
Related papers

Related papers: Latent Autoregressive Source Separation

200 papers

The Goal is to obtain a simple multichannel source separation with very low latency. Applications can be teleconferencing, hearing aids, augmented reality, or selective active noise cancellation. These real time applications need a very low…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-13 Gerald Schuller

We introduce SLED, an alternative approach to speech language modeling by encoding speech waveforms into sequences of continuous latent representations and modeling them autoregressively using an energy distance objective. The energy…

Computation and Language · Computer Science 2025-10-27 Zhengrui Ma , Yang Feng , Chenze Shao , Fandong Meng , Jie Zhou , Min Zhang

Standard autoregressive seq2seq models are easily trained by max-likelihood, but tend to show poor results under small-data conditions. We introduce a class of seq2seq models, GAMs (Global Autoregressive Models), which combine an…

Machine Learning · Computer Science 2019-09-23 Tetiana Parshakova , Jean-Marc Andreoli , Marc Dymetman

Research on audio generation has progressively developed along both waveform-based and spectrogram-based directions, giving rise to diverse strategies for representing and generating audio. At the same time, advances in image synthesis have…

Sound · Computer Science 2026-04-17 Eleonora Ristori , Luca Bindini , Paolo Frasconi

Autoregressive models for text sometimes generate repetitive and low-quality output because errors accumulate during the steps of generation. This issue is often attributed to exposure bias - the difference between how a model is trained,…

Computation and Language · Computer Science 2024-03-26 Yizhe Zhang , Jiatao Gu , Zhuofeng Wu , Shuangfei Zhai , Josh Susskind , Navdeep Jaitly

Latent-based image generative models, such as Latent Diffusion Models (LDMs) and Mask Image Models (MIMs), have achieved notable success in image generation tasks. These models typically leverage reconstructive autoencoders like VQGAN or…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Yongxin Zhu , Bocheng Li , Hang Zhang , Xin Li , Linli Xu , Lidong Bing

We present Visual AutoRegressive modeling (VAR), a new generation paradigm that redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or "next-resolution prediction", diverging from the standard…

Computer Vision and Pattern Recognition · Computer Science 2024-06-11 Keyu Tian , Yi Jiang , Zehuan Yuan , Bingyue Peng , Liwei Wang

The ability to automatically generate music that appropriately matches an arbitrary input track is a challenging task. We present a novel controllable system for generating single stems to accompany musical mixes of arbitrary length. At the…

Sound · Computer Science 2024-02-05 Marco Pasini , Maarten Grachten , Stefan Lattner

Autoregressive models have emerged as a powerful approach for visual generation but suffer from slow inference speed due to their sequential token-by-token prediction process. In this paper, we propose a simple yet effective approach for…

Computer Vision and Pattern Recognition · Computer Science 2025-04-04 Yuqing Wang , Shuhuai Ren , Zhijie Lin , Yujin Han , Haoyuan Guo , Zhenheng Yang , Difan Zou , Jiashi Feng , Xihui Liu

Novelty detection is commonly referred to as the discrimination of observations that do not conform to a learned model of regularity. Despite its importance in different application settings, designing a novelty detector is utterly complex…

Computer Vision and Pattern Recognition · Computer Science 2019-03-07 Davide Abati , Angelo Porrello , Simone Calderara , Rita Cucchiara

Masked diffusion models have demonstrated competitive results on various tasks including language generation. However, due to its iterative refinement process, the inference is often bottlenecked by slow and static sampling speed. To…

Machine Learning · Computer Science 2026-03-09 Seo Hyun Kim , Sunwoo Hong , Hojung Jung , Youngrok Park , Se-Young Yun

Neural samplers such as variational autoencoders (VAEs) or generative adversarial networks (GANs) approximate distributions by transforming samples from a simple random source---the latent space---to samples from a more complex distribution…

Machine Learning · Statistics 2018-02-09 Nutan Chen , Alexej Klushyn , Richard Kurle , Xueyan Jiang , Justin Bayer , Patrick van der Smagt

Deep spatially selective filters achieve high-quality enhancement with real-time capable architectures for stationary speakers of known directions. To retain this level of performance in dynamic scenarios when only the speakers' initial…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-26 Jakob Kienegger , Timo Gerkmann

Each training step for a variational autoencoder (VAE) requires us to sample from the approximate posterior, so we usually choose simple (e.g. factorised) approximate posteriors in which sampling is an efficient computation that fully…

Machine Learning · Statistics 2018-05-29 Laurence Aitchison , Vincent Adam , Srinivas C. Turaga

Visual autoregressive modeling, based on the next-scale prediction paradigm, exhibits notable advantages in image quality and model scalability over traditional autoregressive and diffusion models. It generates images by progressively…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Zhuokun Chen , Jugang Fan , Zhuowei Yu , Bohan Zhuang , Mingkui Tan

Variational Autoencoders (VAEs) are well-established as a principled approach to probabilistic unsupervised learning with neural networks. Typically, an encoder network defines the parameters of a Gaussian distributed latent space from…

Machine Learning · Computer Science 2025-05-16 Alan Jeffares , Liyuan Liu

Despite substantial progress in anomaly synthesis methods, existing diffusion-based and coarse inpainting pipelines commonly suffer from structural deficiencies such as micro-structural discontinuities, limited semantic controllability, and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-06 Long Qian , Bingke Zhu , Yingying Chen , Ming Tang , Jinqiao Wang

While inference-time scaling through search has revolutionized Large Language Models, translating these gains to image generation has proven difficult. Recent attempts to apply search strategies to continuous diffusion models show limited…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Erik Riise , Mehmet Onurcan Kaya , Dim P. Papadopoulos

Discrete diffusion models have emerged as a powerful class of models and a promising route to fast language generation, but practical implementations typically rely on factored reverse transitions ignoring cross-token dependencies and…

Machine Learning · Computer Science 2026-05-14 Dario Shariatian , Alain Durmus , Umut Simsekli , Stefano Peluchetti

An ability to model a generative process and learn a latent representation for speech in an unsupervised fashion will be crucial to process vast quantities of unlabelled speech data. Recently, deep probabilistic generative models such as…

Computation and Language · Computer Science 2017-09-25 Wei-Ning Hsu , Yu Zhang , James Glass