English
Related papers

Related papers: Diffusion-Based Speech Enhancement with Joint Gene…

200 papers

Latent diffusion models (LDMs) enable high-fidelity synthesis by operating in learned latent spaces. However, training state-of-the-art LDMs requires complex staging: a tokenizer must be trained first, before the diffusion model can be…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Shivam Duggal , Xingjian Bai , Zongze Wu , Richard Zhang , Eli Shechtman , Antonio Torralba , Phillip Isola , William T. Freeman

This paper introduces a discrete diffusion model (DDM) framework for text-aligned speech tokenization and reconstruction. By replacing the auto-regressive speech decoder with a discrete diffusion counterpart, our model achieves…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-25 Pin-Jui Ku , He Huang , Jean-Marie Lemercier , Subham Sekhar Sahoo , Zhehuai Chen , Ante Jukić

There are many deterministic mathematical operations (e.g. compression, clipping, downsampling) that degrade speech quality considerably. In this paper we introduce a neural network architecture, based on a modification of the DiffWave…

Sound · Computer Science 2021-09-03 Jianwei Zhang , Suren Jayasuriya , Visar Berisha

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

Machine Learning · Computer Science 2021-06-17 Eliya Nachmani , Robin San Roman , Lior Wolf

Despite successful applications of end-to-end approaches in multi-channel speech recognition, the performance still degrades severely when the speech is corrupted by reverberation. In this paper, we integrate the dereverberation module into…

Audio and Speech Processing · Electrical Eng. & Systems 2021-11-18 Wangyou Zhang , Aswin Shanmugam Subramanian , Xuankai Chang , Shinji Watanabe , Yanmin Qian

Diffusion models has emerged as a powerful framework for tasks like image controllable generation and dense prediction. However, existing models often struggle to capture underlying semantics (e.g., edges, textures, shapes) and effectively…

Computer Vision and Pattern Recognition · Computer Science 2025-03-07 Zhong Ji , Weilong Cao , Yan Zhang , Yanwei Pang , Jungong Han , Xuelong Li

Diffusion models are trained by learning a sequence of models that reverse each step of noise corruption. Typically, the model parameters are fully shared across multiple timesteps to enhance training efficiency. However, since the…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Qianli Ma , Xuefei Ning , Dongrui Liu , Li Niu , Linfeng Zhang

Singing voice conversion (SVC) is one promising technique which can enrich the way of human-computer interaction by endowing a computer the ability to produce high-fidelity and expressive singing voice. In this paper, we propose DiffSVC, an…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-31 Songxiang Liu , Yuewen Cao , Dan Su , Helen Meng

We propose in this paper an analytically new construct of a diffusion model whose drift and diffusion parameters yield an exponentially time-decaying Signal to Noise Ratio in the forward process. In reverse, the construct cleverly carries…

Image and Video Processing · Electrical Eng. & Systems 2024-08-16 Tanmay Asthana , Yufang Bao , Hamid Krim

We present a supervised learning framework of training generative models for density estimation. Generative models, including generative adversarial networks, normalizing flows, variational auto-encoders, are usually considered as…

Machine Learning · Computer Science 2023-10-24 Yanfang Liu , Minglei Yang , Zezhong Zhang , Feng Bao , Yanzhao Cao , Guannan Zhang

Modern speech enhancement (SE) networks typically implement noise suppression through time-frequency masking, latent representation masking, or discriminative signal prediction. In contrast, some recent works explore SE via generative…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-07 Bryce Irvin , Marko Stamenovic , Mikolaj Kegler , Li-Chia Yang

The problem of speech separation, also known as the cocktail party problem, refers to the task of isolating a single speech signal from a mixture of speech signals. Previous work on source separation derived an upper bound for the source…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-27 Shahar Lutati , Eliya Nachmani , Lior Wolf

Diffusion models have recently set new benchmarks in Speech Enhancement (SE). However, most existing score-based models treat speech spectrograms merely as generic 2D images, applying uniform processing that ignores the intrinsic structural…

Sound · Computer Science 2026-02-03 Ke Xue , Rongfei Fan , Kai Li , Shanping Yu , Puning Zhao , Jianping An

Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent…

Sound · Computer Science 2022-04-19 Jen-Cheng Hou , Syu-Siang Wang , Ying-Hui Lai , Yu Tsao , Hsiu-Wen Chang , Hsin-Min Wang

Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent…

Sound · Computer Science 2018-01-25 Jen-Cheng Hou , Syu-Siang Wang , Ying-Hui Lai , Yu Tsao , Hsiu-Wen Chang , Hsin-Min Wang

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…

Computation and Language · Computer Science 2026-03-06 Jia-Nan Li , Jian Guan , Wei Wu , Chongxuan Li

Speech enhancement is an essential task of improving speech quality in noise scenario. Several state-of-the-art approaches have introduced visual information for speech enhancement,since the visual aspect of speech is essentially unaffected…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-21 Xinmeng Xu , Yang Wang , Dongxiang Xu , Yiyuan Peng , Cong Zhang , Jie Jia , Binbin Chen

In typical multi-talker speech recognition systems, a neural network-based acoustic model predicts senone state posteriors for each speaker. These are later used by a single-talker decoder which is applied on each speaker-specific output…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-18 Martin Kocour , Kateřina Žmolíková , Lucas Ondel , Ján Švec , Marc Delcroix , Tsubasa Ochiai , Lukáš Burget , Jan Černocký

Nowadays, denoising diffusion probabilistic models have been adapted for many image segmentation tasks. However, existing end-to-end models have already demonstrated remarkable capabilities. Rather than using denoising diffusion…

Computer Vision and Pattern Recognition · Computer Science 2023-12-07 Shi Zhenning , Dong Changsheng , Xie Xueshuo , Pan Bin , He Along , Li Tao

Speculative decoding has emerged as a widely adopted method to accelerate large language model inference without sacrificing the quality of the model outputs. While this technique has facilitated notable speed improvements by enabling…

Computation and Language · Computer Science 2025-02-12 Jacob K Christopher , Brian R Bartoldson , Tal Ben-Nun , Michael Cardei , Bhavya Kailkhura , Ferdinando Fioretto