English
Related papers

Related papers: Stage-adaptive audio diffusion modeling

200 papers

Streaming models are an essential component of real-time speech enhancement tools. The streaming regime constrains speech enhancement models to use only a tiny context of future information. As a result, the low-latency streaming setup is…

Sound · Computer Science 2023-12-06 Pavel Andreev , Nicholas Babaev , Azat Saginbaev , Ivan Shchekotov , Aibek Alanov

This paper introduces an audio-visual speech enhancement system that leverages score-based generative models, also known as diffusion models, conditioned on visual information. In particular, we exploit audio-visual embeddings obtained from…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-05 Julius Richter , Simone Frintrop , Timo Gerkmann

Large diffusion models have been successful in text-to-audio (T2A) synthesis tasks, but they often suffer from common issues such as semantic misalignment and poor temporal consistency due to limited natural language understanding and data…

Diffusion model, as a new generative model which is very popular in image generation and audio synthesis, is rarely used in speech enhancement. In this paper, we use the diffusion model as a module for stochastic refinement. We propose…

Sound · Computer Science 2022-11-01 Zhibin Qiu , Mengfan Fu , Yinfeng Yu , LiLi Yin , Fuchun Sun , Hao Huang

Diffusion models have shown promise in text generation, but often struggle with generating long, coherent, and contextually accurate text. Token-level diffusion doesn't model word-order dependencies explicitly and operates on short, fixed…

Computation and Language · Computer Science 2025-05-27 Xiaochen Zhu , Georgi Karadzhov , Chenxi Whitehouse , Andreas Vlachos

The goal of this paper is to enhance Text-to-Audio generation at inference, focusing on generating realistic audio that precisely aligns with text prompts. Despite the rapid advancements, existing models often fail to achieve a reliable…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-25 Jaemin Jung , Jaehun Kim , Inkyu Shin , Joon Son Chung

Autoregressive (AR) models with diffusion heads have recently achieved strong text-to-audio performance, yet their iterative decoding and multi-step sampling process introduce high-latency issues. To address this bottleneck, we propose a…

We demonstrate how conditional generation from diffusion models can be used to tackle a variety of realistic tasks in the production of music in 44.1kHz stereo audio with sampling-time guidance. The scenarios we consider include…

Sound · Computer Science 2023-12-06 Mark Levy , Bruno Di Giorgi , Floris Weers , Angelos Katharopoulos , Tom Nickson

Self-supervised learning (SSL) on large-scale datasets like AudioSet has become the dominant paradigm for audio representation learning. While the continuous influx of new, unlabeled audio presents an opportunity to enrich these static…

Sound · Computer Science 2026-01-26 Yizhou Zhang , Yuan Gao , Wangjin Zhou , Zicheng Yuan , Keisuke Imoto , Tatsuya Kawahara

Audio self-supervised learning (SSL) pre-training, which aims to learn good representations from unlabeled audio, has made remarkable progress. However, the extensive computational demands during pre-training pose a significant barrier to…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-09 Wenxi Chen , Yuzhe Liang , Ziyang Ma , Zhisheng Zheng , Xie Chen

Diffusion models are instrumental in text-to-audio (TTA) generation. Unfortunately, they suffer from slow inference due to an excessive number of queries to the underlying denoising network per generation. To address this bottleneck, we…

Sound · Computer Science 2024-06-25 Yatong Bai , Trung Dang , Dung Tran , Kazuhito Koishida , Somayeh Sojoudi

Multi-stage learning is an effective technique to invoke multiple deep-learning modules sequentially. This paper applies multi-stage learning to speech enhancement by using a multi-stage structure, where each stage comprises a…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-25 Ju Lin , Adriaan J. van Wijngaarden , Kuang-Ching Wang , Melissa C. Smith

The introduction of diffusion models has brought significant advances to the field of audio-driven talking head generation. However, the extremely slow inference speed severely limits the practical implementation of diffusion-based talking…

Graphics · Computer Science 2025-11-18 Haotian Wang , Yuzhe Weng , Jun Du , Haoran Xu , Xiaoyan Wu , Shan He , Bing Yin , Cong Liu , Jianqing Gao , Qingfeng Liu

Diffusion speech enhancement on discrete audio codec features gain immense attention due to their improved speech component reconstruction capability. However, they usually suffer from high inference computational complexity due to multiple…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-30 Yihui Fu , Tim Fingscheidt

Diffusion models have recently advanced photorealistic human synthesis, although practical talking-head generation (THG) remains constrained by high inference latency, temporal instability such as flicker and identity drift, and imperfect…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Soumya Mazumdar , Vineet Kumar Rakesh

Visual and auditory perception are two crucial ways humans experience the world. Text-to-video generation has made remarkable progress over the past year, but the absence of harmonious audio in generated video limits its broader…

Sound · Computer Science 2025-03-25 Yong Ren , Chenxing Li , Manjie Xu , Wei Liang , Yu Gu , Rilin Chen , Dong Yu

Learning systems deployed in nonstationary and safety-critical environments often suffer from instability, slow convergence, or brittle adaptation when learning dynamics evolve over time. While modern optimization, reinforcement learning,…

Machine Learning · Computer Science 2026-01-05 Akash Samanta , Sheldon Williamson

Performance-score synchronization is an integral task in signal processing, which entails generating an accurate mapping between an audio recording of a performance and the corresponding musical score. Traditional synchronization methods…

Sound · Computer Science 2022-04-20 Ruchit Agrawal , Daniel Wolff , Simon Dixon

Generative AI has demonstrated impressive performance in various fields, among which speech synthesis is an interesting direction. With the diffusion model as the most popular generative model, numerous works have attempted two active…

The Semantic Layered Embedding Diffusion (SLED) mechanism redefines the representation of hierarchical semantics within transformer-based architectures, enabling enhanced contextual consistency across a wide array of linguistic tasks. By…

Computation and Language · Computer Science 2025-03-26 Irin Kabakum , Thomas Montgomery , Daniel Ravenwood , Genevieve Harrington