中文
相关论文

相关论文: Automatic Annotation of XHTML Pages with Audio Com…

200 篇论文

A natural question arising in Music Source Separation (MSS) is whether long range contextual information is useful, or whether local acoustic features are sufficient. In other fields, attention based Transformers have shown their ability to…

音频与语音处理 · 电气工程与系统科学 2022-11-17 Simon Rouard , Francisco Massa , Alexandre Défossez

As the NLP community increasingly addresses challenges associated with multilingualism, robust annotation tools are essential to handle multilingual datasets efficiently. In this paper, we introduce a code-mixed multilingual text annotation…

计算与语言 · 计算机科学 2024-08-07 Rajvee Sheth , Shubh Nisar , Heenaben Prajapati , Himanshu Beniwal , Mayank Singh

Tag-Pag is an application designed to simplify the categorization of web pages, a task increasingly common for researchers who scrape web pages to analyze individuals' browsing patterns or train machine learning classifiers. Unlike existing…

信息检索 · 计算机科学 2025-02-25 Anton Pogrebnjak , Julian Schelb , Andreas Spitz , Celina Kacperski , Roberto Ulloa

Audio-text relevance learning refers to learning the shared semantic properties of audio samples and textual descriptions. The standard approach uses binary relevances derived from pairs of audio samples and their human-provided captions,…

音频与语音处理 · 电气工程与系统科学 2024-08-28 Huang Xie , Khazar Khorrami , Okko Räsänen , Tuomas Virtanen

Contrarily to standard approaches to topic annotation, the technique used in this work does not centrally rely on some sort of -- possibly statistical -- keyword extraction. In fact, the proposed annotation algorithm uses a large scale…

计算与语言 · 计算机科学 2007-05-23 Pierre Andrews , Martin Rajman

We introduce AnnoABSA, the first web-based annotation tool to support the full spectrum of Aspect-Based Sentiment Analysis (ABSA) tasks. The tool is highly customizable, enabling flexible configuration of sentiment elements and…

计算与语言 · 计算机科学 2026-03-03 Nils Constantin Hellwig , Jakob Fehle , Udo Kruschwitz , Christian Wolff

Learned object detection methods based on fusion of LiDAR and camera data require labeled training samples, but niche applications, such as warehouse robotics or automated infrastructure, require semantic classes not available in large…

计算机视觉与模式识别 · 计算机科学 2023-12-07 Ryan Rubel , Andrew Dudash , Mohammad Goli , James O'Hara , Karl Wunderlich

Recent years have seen a significant increase in video content creation and consumption. Crafting engaging content requires the careful curation of both visual and audio elements. While visual cue curation, through techniques like optimal…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Chao Huang , Ruohan Gao , J. M. F. Tsang , Jan Kurcius , Cagdas Bilen , Chenliang Xu , Anurag Kumar , Sanjeel Parekh

The Eureka-147 Digital Audio Broadcasting (DAB) standard defines the 'dynamic labels' data field for holding information about the transmission content. However, this information does not follow a well-defined structure since it is designed…

综合文献 · 计算机科学 2007-05-23 Darran Nathan , Eva Rosdiana , Chua Beng Koon

In recent years, user-generated audio content has proliferated across various media platforms, creating a growing need for efficient retrieval methods that allow users to search for audio clips using natural language queries. This task,…

声音 · 计算机科学 2024-12-31 Haoran Sun , Zimu Wang , Qiuyi Chen , Jianjun Chen , Jia Wang , Haiyang Zhang

Recent progress in multimodal models has spurred rapid advances in audio understanding, generation, and editing. However, these capabilities are typically addressed by specialized models, leaving the development of a truly unified framework…

We introduce a deep learning model for speech denoising, a long-standing challenge in audio analysis arising in numerous applications. Our approach is based on a key observation about human speech: there is often a short pause between each…

声音 · 计算机科学 2020-10-26 Ruilin Xu , Rundi Wu , Yuko Ishiwaka , Carl Vondrick , Changxi Zheng

This paper presents our submitted system to SemEval 2021 Task 4: Reading Comprehension of Abstract Meaning. Our system uses a large pre-trained language model as the encoder and an additional dual multi-head co-attention layer to strengthen…

计算与语言 · 计算机科学 2021-03-31 Yuxin Jiang , Ziyi Shou , Qijun Wang , Hao Wu , Fangzhen Lin

Voice anonymization systems aim to protect speaker privacy by obscuring vocal traits while preserving the linguistic content relevant for downstream applications. However, because these linguistic cues remain intact, they can be exploited…

音频与语音处理 · 电气工程与系统科学 2026-05-21 Ahmad Aloradi , Ünal Ege Gaznepoglu , Emanuël A. P. Habets , Daniel Tenbrinck

Document images often have intricate layout structures, with numerous content regions (e.g. texts, figures, tables) densely arranged on each page. This makes the manual annotation of layout datasets expensive and inefficient. These…

机器学习 · 计算机科学 2021-03-31 Zejiang Shen , Jian Zhao , Melissa Dell , Yaoliang Yu , Weining Li

Automatic mean opinion score (MOS) prediction provides a more perceptual alternative to objective metrics, offering deeper insights into the evaluated models. With the rapid progress of multimodal large language models (MLLMs), their…

声音 · 计算机科学 2025-09-23 Yuhang Jia , Xu Zhang , Yang Chen , Hui Wang , Enzhi Wang , Yong Qin

The Audio Description (AD) task aims to generate descriptions of visual elements for visually impaired individuals to help them access long-form video content, like movies. With video feature, text, character bank and context information as…

计算机视觉与模式识别 · 计算机科学 2025-04-16 Hanlin Wang , Zhan Tong , Kecheng Zheng , Yujun Shen , Limin Wang

We present a node-based storytelling system for multimodal content generation. The system represents stories as graphs of nodes that can be expanded, edited, and iteratively refined through direct user edits and natural-language prompts.…

人机交互 · 计算机科学 2025-11-07 Alexander Htet Kyaw , Lenin Ravindranath Sivalingam

In this work, we open up the DAWT dataset - Densely Annotated Wikipedia Texts across multiple languages. The annotations include labeled text mentions mapping to entities (represented by their Freebase machine ids) as well as the type of…

信息检索 · 计算机科学 2017-03-06 Nemanja Spasojevic , Preeti Bhargava , Guoning Hu

We seek to develop simultaneous segmentation and classification of notes from audio recordings in presence of outliers. The selected architecture for modeling time series is hierarchical linear dynamical system (HLDS). We propose a novel…

声音 · 计算机科学 2022-03-01 Leila Kalantari , Jose Principe , Kathryn E. Sieving