English
Related papers

Related papers: From Coarse to Fine: Efficient Training for Audio …

200 papers

Analog Compute-In-Memory (CIM) architectures promise significant energy efficiency gains for neural network inference, but suffer from complex hardware-induced noise that poses major challenges for deployment. While noise-aware training…

Machine Learning · Computer Science 2025-08-19 Yuannuo Feng , Wenyong Zhou , Yuexi Lyu , Yixiang Zhang , Zhengwu Liu , Ngai Wong , Wang Kang

Audio-Visual Segmentation (AVS) aims to identify and segment sound-producing objects in videos by leveraging both visual and audio modalities. It has emerged as a significant research area in multimodal perception, enabling fine-grained…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Jia Li , Yapeng Tian

The field of audio captioning has seen significant advancements in recent years, driven by the availability of large-scale audio datasets and advancements in deep learning techniques. In this technical report, we present our approach to…

Sound · Computer Science 2023-05-18 Marek Kadlčík , Adam Hájek , Jürgen Kieslich , Radosław Winiecki

We propose an audio-to-audio neural network model that learns to denoise old music recordings. Our model internally converts its input into a time-frequency representation by means of a short-time Fourier transform (STFT), and processes the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-17 Yunpeng Li , Beat Gfeller , Marco Tagliasacchi , Dominik Roblek

Video-to-speech synthesis is the task of reconstructing the speech signal from a silent video of a speaker. Most established approaches to date involve a two-step process, whereby an intermediate representation from the video, such as a…

Sound · Computer Science 2024-10-28 Triantafyllos Kefalas , Yannis Panagakis , Maja Pantic

Drawing inspiration from the hierarchical processing of the human auditory system, which transforms sound from low-level acoustic features to high-level semantic understanding, we introduce a novel coarse-to-fine audio reconstruction…

Sound · Computer Science 2024-05-30 Che Liu , Changde Du , Xiaoyu Chen , Huiguang He

End-to-end Speech Translation (ST) models have many potential advantages when compared to the cascade of Automatic Speech Recognition (ASR) and text Machine Translation (MT) models, including lowered inference latency and the avoidance of…

Computation and Language · Computer Science 2019-02-12 Ye Jia , Melvin Johnson , Wolfgang Macherey , Ron J. Weiss , Yuan Cao , Chung-Cheng Chiu , Naveen Ari , Stella Laurenzo , Yonghui Wu

Audio-based music structure analysis (MSA) is an essential task in Music Information Retrieval that remains challenging due to the complexity and variability of musical form. Recent advances highlight the potential of fine-tuning…

Sound · Computer Science 2025-07-21 Yixiao Zhang , Haonan Chen , Ju-Chiang Wang , Jitong Chen

Recently, foundation models based on Vision Transformers (ViTs) have become widely available. However, their fine-tuning process is highly resource-intensive, and it hinders their adoption in several edge or low-energy applications. To this…

Computer Vision and Pattern Recognition · Computer Science 2024-08-19 Alessio Devoto , Federico Alvetreti , Jary Pomponi , Paolo Di Lorenzo , Pasquale Minervini , Simone Scardapane

Transformer-based large pre-trained models have shown remarkable generalization ability, and various parameter-efficient fine-tuning (PEFT) methods have been proposed to customize these models on downstream tasks with minimal computational…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Zichen Miao , Wei Chen , Qiang Qiu

Vision Transformers (ViTs) have demonstrated superior performance across a wide range of computer vision tasks. However, structured noise artifacts in their feature maps hinder downstream applications such as segmentation and depth…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Sumit Mamtani

Timing systems based on Analog-to-Digital Converters are widely used in the design of previous high energy physics detectors. In this paper, we propose a new method based on deep learning to extract the time information from a finite set of…

Data Analysis, Statistics and Probability · Physics 2019-04-02 Pengcheng Ai , Dong Wang , Guangming Huang , Ni Fang , Deli Xu , Fan Zhang

Continual learning aims to incrementally acquire new concepts in data streams while resisting forgetting previous knowledge. With the rise of powerful pre-trained models (PTMs), there is a growing interest in training incremental learning…

Machine Learning · Computer Science 2024-11-05 Linglan Zhao , Xuerui Zhang , Ke Yan , Shouhong Ding , Weiran Huang

Most deep learning-based multi-channel speech enhancement methods focus on designing a set of beamforming coefficients to directly filter the low signal-to-noise ratio signals received by microphones, which hinders the performance of these…

Sound · Computer Science 2022-02-08 Wenzhe Liu , Andong Li , Chengshi Zheng , Xiaodong Li

Direct speech-to-text translation (ST) models are usually trained on corpora segmented at sentence level, but at inference time they are commonly fed with audio split by a voice activity detector (VAD). Since VAD segmentation is not…

Computation and Language · Computer Science 2020-08-06 Marco Gaido , Mattia Antonino Di Gangi , Matteo Negri , Mauro Cettolo , Marco Turchi

The problem of recovering a signal from the magnitude of its short-time Fourier transform (STFT) is a longstanding one in audio signal processing. Existing approaches rely on heuristics that often perform poorly because of the nonconvexity…

Applications · Statistics 2012-09-11 Dennis L. Sun , Julius O. Smith

Self-supervised pre-training using so-called "pretext" tasks has recently shown impressive performance across a wide range of modalities. In this work, we advance self-supervised learning from permutations, by pre-training a model to…

Sound · Computer Science 2021-05-05 Andrew N Carr , Quentin Berthet , Mathieu Blondel , Olivier Teboul , Neil Zeghidour

Scalable training of large models (like BERT and GPT-3) requires careful optimization rooted in model design, architecture, and system capabilities. From a system standpoint, communication has become a major bottleneck, especially on…

Machine Learning · Computer Science 2021-07-01 Hanlin Tang , Shaoduo Gan , Ammar Ahmad Awan , Samyam Rajbhandari , Conglong Li , Xiangru Lian , Ji Liu , Ce Zhang , Yuxiong He

This paper presents an audio visual automatic speech recognition (AV-ASR) system using a Transformer-based architecture. We particularly focus on the scene context provided by the visual information, to ground the ASR. We extract…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-01 Georgios Paraskevopoulos , Srinivas Parthasarathy , Aparna Khare , Shiva Sundaram

Multi-channel acoustic signal processing is a well-established and powerful tool to exploit the spatial diversity between a target signal and non-target or noise sources for signal enhancement. However, the textbook solutions for optimal…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-14 Reinhold Haeb-Umbach , Tomohiro Nakatani , Marc Delcroix , Christoph Boeddeker , Tsubasa Ochiai
‹ Prev 1 4 5 6 7 8 10 Next ›