English
Related papers

Related papers: Improving Robustness of Diffusion-Based Zero-Shot …

200 papers

Diffusion probabilistic models have been recently used in a variety of tasks, including speech enhancement and synthesis. As a generative approach, diffusion models have been shown to be especially suitable for imputation problems, where…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-05 Tal Peer , Simon Welker , Timo Gerkmann

Over 70 million people worldwide experience stuttering, yet most automatic speech systems misinterpret disfluent utterances or fail to transcribe them accurately. Existing methods for stutter correction rely on handcrafted feature…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-06 Qianheng Xu

Recent advances in talking face generation have significantly improved facial animation synthesis. However, existing approaches face fundamental limitations: 3DMM-based methods maintain temporal consistency but lack fine-grained regional…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Kangwei Liu , Junwu Liu , Yun Cao , Jinlin Guo , Xiaowei Yi

Generating long-form 44.1kHz stereo audio from text prompts can be computationally demanding. Further, most previous works do not tackle that music and sound effects naturally vary in their duration. Our research focuses on the efficient…

Sound · Computer Science 2024-05-14 Zach Evans , CJ Carr , Josiah Taylor , Scott H. Hawley , Jordi Pons

Conversational speech synthesis (CSS) aims to synthesize both contextually appropriate and expressive speech, and considerable efforts have been made to enhance the understanding of conversational context. However, existing CSS systems are…

Sound · Computer Science 2025-02-28 Weihao wu , Zhiwei Lin , Yixuan Zhou , Jingbei Li , Rui Niu , Qinghua Wu , Songjun Cao , Long Ma , Zhiyong Wu

Diffusion models have gained attention in speech enhancement tasks, providing an alternative to conventional discriminative methods. However, research on target speech extraction under multi-speaker noisy conditions remains relatively…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-08 Leying Zhang , Yao Qian , Linfeng Yu , Heming Wang , Hemin Yang , Long Zhou , Shujie Liu , Yanmin Qian

This work introduces Sample-Efficient Speech Diffusion (SESD), an algorithm for effective speech synthesis in modest data regimes through latent diffusion. It is based on a novel diffusion architecture, that we call U-Audio Transformer…

Sound · Computer Science 2024-09-06 Justin Lovelace , Soham Ray , Kwangyoun Kim , Kilian Q. Weinberger , Felix Wu

With read-aloud speech synthesis achieving high naturalness scores, there is a growing research interest in synthesising spontaneous speech. However, human spontaneous face-to-face conversation has both spoken and non-verbal aspects (here,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-15 Shivam Mehta , Siyang Wang , Simon Alexanderson , Jonas Beskow , Éva Székely , Gustav Eje Henter

The latency bottleneck of traditional text-to-speech (TTS) systems fundamentally hinders the potential of streaming large language models (LLMs) in conversational AI. These TTS systems, typically trained and inferenced on complete…

Computation and Language · Computer Science 2025-05-27 Richard He Bai , Zijin Gu , Tatiana Likhomanenko , Navdeep Jaitly

Diffusion models have shown impressive potential on talking head generation. While plausible appearance and talking effect are achieved, these methods still suffer from temporal, 3D or expression inconsistency due to the error accumulation…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Haijie Yang , Zhenyu Zhang , Hao Tang , Jianjun Qian , Jian Yang

Recent advancements in speech synthesis have enabled large language model (LLM)-based systems to perform zero-shot generation with controllable content, timbre, speaker identity, and emotion through input prompts. As a result, these models…

Stuttering is a speech disorder where the natural flow of speech is interrupted by blocks, repetitions or prolongations of syllables, words and phrases. The majority of existing automatic speech recognition (ASR) interfaces perform poorly…

Recently, conditional score-based diffusion models have gained significant attention in the field of supervised speech enhancement, yielding state-of-the-art performance. However, these methods may face challenges when generalising to…

Computer Vision and Pattern Recognition · Computer Science 2023-09-20 Berné Nortier , Mostafa Sadeghi , Romain Serizel

Text-to-speech (TTS) technology has achieved impressive results for widely spoken languages, yet many under-resourced languages remain challenged by limited data and linguistic complexities. In this paper, we present a novel methodology…

Sound · Computer Science 2025-04-11 Yizhong Geng , Jizhuo Xu , Zeyu Liang , Jinghan Yang , Xiaoyi Shi , Xiaoyu Shen

Diffusion models are a new class of generative models that have shown outstanding performance in image generation literature. As a consequence, studies have attempted to apply diffusion models to other tasks, such as speech enhancement. A…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-10 Philippe Gonzalez , Zheng-Hua Tan , Jan Østergaard , Jesper Jensen , Tommy Sonne Alstrøm , Tobias May

Stable Audio 3 is a family of fast latent diffusion models (small, medium, large) for variable-length audio generation and editing. Since our models can generate several minutes of audio, variable-length generations are key to avoid the…

Sound · Computer Science 2026-05-19 Zach Evans , Julian D. Parker , Matthew Rice , CJ Carr , Zack Zukowski , Josiah Taylor , Jordi Pons

Recent advances in zero-shot text-to-speech (TTS) synthesis have achieved high-quality speech generation for unseen speakers, but most systems remain unsuitable for real-time applications because of their offline design. Current streaming…

Sound · Computer Science 2025-06-17 Hui Wang , Yifan Yang , Shujie Liu , Jinyu Li , Lingwei Meng , Yanqing Liu , Jiaming Zhou , Haoqin Sun , Yan Lu , Yong Qin

Diffusion Transformers (DiTs) have achieved remarkable success in diverse and high-quality text-to-image(T2I) generation. However, how text and image latents individually and jointly contribute to the semantics of generated images, remain…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Zitao Shuai , Chenwei Wu , Zhengxu Tang , Bowen Song , Liyue Shen

The task of steel surface defect recognition is an industrial problem with great industry values. The data insufficiency is the major challenge in training a robust defect recognition network. Existing methods have investigated to enlarge…

Computer Vision and Pattern Recognition · Computer Science 2024-05-06 Yichun Tai , Kun Yang , Tao Peng , Zhenzhen Huang , Zhijiang Zhang

In recent years, diffusion based methods have emerged as a powerful paradigm for generative modeling. Although discrete diffusion for natural language processing has been explored to a lesser extent, it shows promise for tasks requiring…

Machine Learning · Computer Science 2025-03-25 Andrew Kiruluta , Andreas Lemos