English
Related papers

Related papers: From Image to Music Language: A Two-Stage Structur…

200 papers

This article presents a benchmark study of symbolic piano music classification using the masked language modelling approach of the Bidirectional Encoder Representations from Transformers (BERT). Specifically, we consider two types of MIDI…

Sound · Computer Science 2024-04-16 Yi-Hui Chou , I-Chun Chen , Chin-Jui Chang , Joann Ching , Yi-Hsuan Yang

Optical Chemical Structure Recognition (OCSR) is critical for converting 2D molecular diagrams from printed literature into machine-readable formats. While Vision-Language Models have shown promise in end-to-end OCR tasks, their direct…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Haocheng Tang , Xingyu Dang , Junmei Wang

In the realm of music AI, arranging rich and structured multi-track accompaniments from a simple lead sheet presents significant challenges. Such challenges include maintaining track cohesion, ensuring long-term coherence, and optimizing…

Sound · Computer Science 2024-11-26 Jingwei Zhao , Gus Xia , Ziyu Wang , Ye Wang

The goal of score following is to track a musical performance, usually in the form of audio, in a corresponding score representation. Established methods mainly rely on computer-readable scores in the form of MIDI or MusicXML and achieve…

Machine Learning · Computer Science 2019-10-17 Florian Henkel , Rainer Kelz , Gerhard Widmer

Visual sound localization is a typical and challenging problem that predicts the location of objects corresponding to the sound source in a video. Previous methods mainly used the audio-visual association between global audio and one-scale…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Shentong Mo , Haofan Wang

One of the challenges in computational acoustics is the identification of models that can simulate and predict the physical behavior of a system generating an acoustic signal. Whenever such models are used for commercial applications an…

Real-time music tracking systems follow a musical performance and at any time report the current position in a corresponding score. Most existing methods approach this problem exclusively in the audio domain, typically using online time…

Sound · Computer Science 2025-05-09 Silvan Peter , Patricia Hu , Gerhard Widmer

Subword tokenization has been widely successful in text-based natural language processing (NLP) tasks with Transformer-based models. As Transformer models become increasingly popular in symbolic music-related studies, it is imperative to…

Sound · Computer Science 2023-04-26 Adarsh Kumar , Pedro Sarmento

This study investigates the problem of angle-based localization of multiple targets using a multistatic OFDM radar. Although the maximum likelihood (ML) approach can be employed to merge data from different radar pairs, this method requires…

Signal Processing · Electrical Eng. & Systems 2024-04-30 Martin Willame , Hasan Can Yildirim , Laurent Storrer , François Horlin , Jérôme Louveaux

Modelling musical structure is vital yet challenging for artificial intelligence systems that generate symbolic music compositions. This literature review dissects the evolution of techniques for incorporating coherent structure, from…

Sound · Computer Science 2024-03-14 Keshav Bhandari , Simon Colton

Chord recognition systems depend on robust feature extraction pipelines. While these pipelines are traditionally hand-crafted, recent advances in end-to-end machine learning have begun to inspire researchers to explore data-driven methods…

Machine Learning · Computer Science 2016-12-16 Filip Korzeniowski , Gerhard Widmer

Assuming unknown classes could be present during classification, the open set recognition (OSR) task aims to classify an instance into a known class or reject it as unknown. In this paper, we use a two-stage training strategy for the OSR…

Computer Vision and Pattern Recognition · Computer Science 2022-09-30 Jingyun Jia , Philip K. Chan

A key aspect of machine learning models lies in their ability to learn efficient intermediate features. However, the input representation plays a crucial role in this process, and polyphonic musical scores remain a particularly complex type…

Machine Learning · Computer Science 2021-09-09 Mathieu Prang , Philippe Esling

The rise of multi-modal search requests from users has highlighted the importance of multi-modal retrieval (i.e. image-to-text or text-to-image retrieval), yet the more complex task of image-to-multi-modal retrieval, crucial for many…

Information Retrieval · Computer Science 2024-06-11 Zida Cheng , Chen Ju , Shuai Xiao , Xu Chen , Zhonghua Zhai , Xiaoyi Zeng , Weilin Huang , Junchi Yan

Video-to-audio (V2A) generation aims to produce corresponding audio given silent video inputs. This task is particularly challenging due to the cross-modality and sequential nature of the audio-visual features involved. Recent works have…

Sound · Computer Science 2024-09-17 Mingjing Yi , Ming Li

This paper gives an overview of our current Optical Music Recognition (OMR) research. We recently released the OMR dataset \emph{DeepScores} as well as the object detection method \emph{Deep Watershed Detector}. We are currently taking some…

Computer Vision and Pattern Recognition · Computer Science 2018-10-15 Ismail Elezi , Lukas Tuggener , Marcello Pelillo , Thilo Stadelmann

A line of a bilingual document page may contain text words in regional language and numerals in English. For Optical Character Recognition (OCR) of such a document page, it is necessary to identify different script forms before running an…

Computer Vision and Pattern Recognition · Computer Science 2011-07-05 B. V. Dhandra , Mallikarjun Hangarge

In this paper, we explore the intersection of technology and cultural preservation by developing a self-supervised learning framework for the classification of musical symbols in historical manuscripts. Optical Music Recognition (OMR) plays…

Information Retrieval · Computer Science 2024-11-26 Elona Shatri , Daniel Raymond , George Fazekas

Music enhances video narratives and emotions, driving demand for automatic video-to-music (V2M) generation. However, existing V2M methods relying solely on visual features or supplementary textual inputs generate music in a black-box…

Multimedia · Computer Science 2025-07-29 Junxian Wu , Weitao You , Heda Zuo , Dengming Zhang , Pei Chen , Lingyun Sun

The current paradigm for creating and deploying immersive audio content is based on audio objects, which are composed of an audio track and position metadata. While rendering an object-based production into a multichannel mix is…

Sound · Computer Science 2021-12-22 Daniel Arteaga , Jordi Pons