English
Related papers

Related papers: DGMO: Training-Free Audio Source Separation throug…

200 papers

Diffusion models have demonstrated high-quality performance in conditional text-to-image generation, particularly with structural cues such as edges, layouts, and depth. However, lighting conditions have received limited attention and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Ryugo Morita , Stanislav Frolov , Brian Bernhard Moser , Ko Watanabe , Riku Takahashi , Andreas Dengel

State of the art audio source separation models rely on supervised data-driven approaches, which can be expensive in terms of labeling resources. On the other hand, approaches for training these models without any direct supervision are…

Machine Learning · Computer Science 2022-04-04 Michele Mancusi , Emilian Postolache , Giorgio Mariani , Marco Fumero , Andrea Santilli , Luca Cosmo , Emanuele Rodolà

Recent attempts to interleave autoregressive (AR) sketchers with diffusion-based refiners over continuous speech representations have shown promise, but they remain brittle under distribution shift and offer limited levers for…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-17 Yakun Song , Xiaobin Zhuang , Jiawei Chen , Zhikang Niu , Guanrou Yang , Chenpeng Du , Dongya Jia , Zhuo Chen , Yuping Wang , Yuxuan Wang , Xie Chen

Masked diffusion language models (MDLMs) promise fast, non-autoregressive text generation, yet existing samplers, which pick tokens to unmask based on model confidence, ignore interactions when unmasking multiple positions in parallel and…

Computation and Language · Computer Science 2026-05-26 Omer Luxembourg , Haim Permuter , Eliya Nachmani

Masked diffusion models (MDMs) have emerged as a popular research topic for generative modeling of discrete data, thanks to their superior performance over other discrete diffusion models, and are rivaling the auto-regressive models (ARMs)…

Machine Learning · Computer Science 2025-05-01 Kaiwen Zheng , Yongxin Chen , Hanzi Mao , Ming-Yu Liu , Jun Zhu , Qinsheng Zhang

In this paper, we propose a two-step training procedure for source separation via a deep neural network. In the first step we learn a transform (and it's inverse) to a latent space where masking-based separation performance using oracles is…

Machine Learning · Computer Science 2021-05-12 Efthymios Tzinis , Shrikant Venkataramani , Zhepei Wang , Cem Subakan , Paris Smaragdis

Masked diffusion language models (MDLMs) have recently emerged as a promising alternative to autoregressive (AR) language models, offering properties such as parallel decoding, flexible generation orders, and the potential for fewer…

Computation and Language · Computer Science 2025-09-30 Jingyi Yang , Guanxu Chen , Xuhao Hu , Jing Shao

Autoregressive models have achieved impressive results over a wide range of domains in terms of generation quality and downstream task performance. In the continuous domain, a key factor behind this success is the usage of quantized latent…

Machine Learning · Computer Science 2023-01-23 Emilian Postolache , Giorgio Mariani , Michele Mancusi , Andrea Santilli , Luca Cosmo , Emanuele Rodolà

Audio diffusion models can synthesize a wide variety of sounds. Existing models often operate on the latent domain with cascaded phase recovery modules to reconstruct waveform. This poses challenges when generating high-fidelity audio. In…

Sound · Computer Science 2023-11-21 Ge Zhu , Yutong Wen , Marc-André Carbonneau , Zhiyao Duan

The immense scale of the recent large language models (LLM) allows many interesting properties, such as, instruction- and chain-of-thought-based fine-tuning, that has significantly improved zero- and few-shot performance in many natural…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-30 Deepanway Ghosal , Navonil Majumder , Ambuj Mehrish , Soujanya Poria

Autoregressive next-token prediction with the Transformer decoder has become a de facto standard in large language models (LLMs), achieving remarkable success in Natural Language Processing (NLP) at scale. Extending this paradigm to audio…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-15 Shu-wen Yang , Byeonggeun Kim , Kuan-Po Huang , Qingming Tang , Huy Phan , Bo-Ru Lu , Harsha Sundar , Shalini Ghosh , Hung-yi Lee , Chieh-Chi Kao , Chao Wang

Zero-shot audio classification aims to recognize and classify a sound class that the model has never seen during training. This paper presents a novel approach for zero-shot audio classification using automatically generated sound attribute…

Sound · Computer Science 2024-07-22 Xuenan Xu , Pingyue Zhang , Ming Yan , Ji Zhang , Mengyue Wu

We present FLAMO, a Frequency-sampling Library for Audio-Module Optimization designed to implement and optimize differentiable linear time-invariant audio systems. The library is open-source and built on the frequency-sampling filter design…

Audio and Speech Processing · Electrical Eng. & Systems 2025-04-15 Gloria Dal Santo , Gian Marco De Bortoli , Karolina Prawda , Sebastian J. Schlecht , Vesa Välimäki

Recent progress in self-supervised or unsupervised machine learning has opened the possibility of building a full speech processing system from raw audio without using any textual representations or expert labels such as phonemes,…

Computation and Language · Computer Science 2022-10-31 Ewan Dunbar , Nicolas Hamilakis , Emmanuel Dupoux

Supervised speech separation uses supervised learning algorithms to learn a mapping from an input noisy signal to an output target. With the fast development of deep learning, supervised separation has become the most important direction in…

Sound · Computer Science 2017-09-05 Shasha Xia , Hao Li , Xueliang Zhang

We enhance the vanilla adversarial training method for unsupervised Automatic Speech Recognition (ASR) by a diffusion-GAN. Our model (1) injects instance noises of various intensities to the generator's output and unlabeled reference text…

Computation and Language · Computer Science 2023-03-27 Xianchao Wu

Generative diffusion processes are an emerging and effective tool for image and speech generation. In the existing methods, the underlying noise distribution of the diffusion process is Gaussian noise. However, fitting distributions with…

Signal Processing · Electrical Eng. & Systems 2021-10-13 Eliya Nachmani , Robin San Roman , Lior Wolf

Sign language generation (SLG) aims to translate written texts into expressive sign motions, bridging communication barriers for the Deaf and Hard-of-Hearing communities. Recent studies formulate SLG within the language modeling framework…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Ronglai Zuo , Rolandos Alexandros Potamias , Qi Sun , Evangelos Ververas , Jiankang Deng , Stefanos Zafeiriou

Diffusion language models are a promising alternative to autoregressive models due to their potential for faster generation. Among discrete diffusion approaches, Masked diffusion currently dominates, largely driven by strong perplexity on…

Machine Learning · Computer Science 2026-02-17 Subham Sekhar Sahoo , Jean-Marie Lemercier , Zhihan Yang , Justin Deschenaux , Jingyu Liu , John Thickstun , Ante Jukic

We showcase an unsupervised method that repurposes deep models trained for music generation and music tagging for audio source separation, without any retraining. An audio generation model is conditioned on an input mixture, producing a…

Sound · Computer Science 2021-10-26 Ethan Manilow , Patrick O'Reilly , Prem Seetharaman , Bryan Pardo