中文
相关论文

相关论文: InaGVAD : a Challenging French TV and Radio Corpus…

200 篇论文

Recent advances in audio generation led to an increasing number of deepfakes, making the general public more vulnerable to financial scams, identity theft, and misinformation. Audio deepfake detectors promise to alleviate this issue, with…

We present UniTalk, a novel dataset specifically designed for the task of active speaker detection, emphasizing challenging scenarios to enhance model generalization. Unlike previously established benchmarks such as AVA, which predominantly…

We present STT4SG-350 (Speech-to-Text for Swiss German), a corpus of Swiss German speech, annotated with Standard German text at the sentence level. The data is collected using a web app in which the speakers are shown Standard German…

Sarcasm is a complex form of figurative language in which the intended meaning contradicts the literal one. Its prevalence in social media and popular culture poses persistent challenges for natural language understanding, sentiment…

计算与语言 · 计算机科学 2026-03-05 Aaron Scott , Maike Züfle , Jan Niehues

We present the Tongue and Lips corpus (TaL), a multi-speaker corpus of audio, ultrasound tongue imaging, and lip videos. TaL consists of two parts: TaL1 is a set of six recording sessions of one professional voice talent, a male native…

音频与语音处理 · 电气工程与系统科学 2020-11-20 Manuel Sam Ribeiro , Jennifer Sanger , Jing-Xuan Zhang , Aciel Eshky , Alan Wrench , Korin Richmond , Steve Renals

Text-to-video (T2V) generation has recently attracted considerable attention, resulting in the development of numerous high-quality datasets that have propelled progress in this area. However, existing public datasets are primarily composed…

计算机视觉与模式识别 · 计算机科学 2025-07-03 Yiming Ju , Jijin Hu , Zhengxiong Luo , Haoge Deng , hanyu Zhao , Li Du , Chengwei Wu , Donglin Hao , Xinlong Wang , Tengfei Pan

In the realm of digital audio processing, Voice Activity Detection (VAD) plays a pivotal role in distinguishing speech from non-speech elements, a task that becomes increasingly complex in noisy environments. This paper details the…

声音 · 计算机科学 2023-12-12 Joshua Ball

Computational auditory scene analysis is gaining interest in the last years. Trailing behind the more mature field of speech recognition, it is particularly general sound event detection that is attracting increasing attention. Crucial for…

声音 · 计算机科学 2020-01-03 Ivo Trowitzsch , Jalil Taghia , Youssef Kashef , Klaus Obermayer

This paper describes our initial efforts to build a large-scale speaker diarization (SD) and identification system on a recently digitized radio broadcast archive from the Netherlands which has more than 6500 audio tapes with 3000 hours of…

计算与语言 · 计算机科学 2019-07-01 Emre Yılmaz , Adem Derinel , Zhou Kun , Henk van den Heuvel , Niko Brummer , Haizhou Li , David A. van Leeuwen

Multi-Modal automatic speech recognition (ASR) techniques aim to leverage additional modalities to improve the performance of speech recognition systems. While existing approaches primarily focus on video or contextual information, the…

声音 · 计算机科学 2023-12-27 Haoxu Wang , Fan Yu , Xian Shi , Yuezhang Wang , Shiliang Zhang , Ming Li

We present a novel corpus for French dialect identification comprising 413,522 French text samples collected from public news websites in Belgium, Canada, France and Switzerland. To ensure an accurate estimation of the dialect…

计算与语言 · 计算机科学 2022-12-16 Mihaela Gaman , Adrian-Gabriel Chifu , William Domingues , Radu Tudor Ionescu

Voice Activity Detection (VAD) aims at detecting speech segments on an audio signal, which is a necessary first step for many today's speech based applications. Current state-of-the-art methods focus on training a neural network exploiting…

音频与语音处理 · 电气工程与系统科学 2022-09-23 Sina Alisamir , Fabien Ringeval , Francois Portet

Despite 230 million speakers, Urdu remains critically under-resourced in speech technology. We introduce UrduSpeech: a large high-fidelity Urdu corpus comprising 156 hours of audio with 12-dimension paralinguistic metadata, encompassing…

音频与语音处理 · 电气工程与系统科学 2026-05-19 Attia Nafees ul Haq , Zeyu Zhu , Jingbin Hu , ChunJiang He , Lei Xie

Our goal is to collect a large-scale audio-visual dataset with low label noise from videos in the wild using computer vision techniques. The resulting dataset can be used for training and evaluating audio recognition models. We make three…

计算机视觉与模式识别 · 计算机科学 2020-09-28 Honglie Chen , Weidi Xie , Andrea Vedaldi , Andrew Zisserman

Improving the performance of end-to-end ASR models on long utterances ranging from minutes to hours in length is an ongoing challenge in speech recognition. A common solution is to segment the audio in advance using a separate voice…

In the context of low-resource languages, the Algerian dialect (AD) faces challenges due to the absence of annotated corpora, hindering its effective processing, notably in Machine Learning (ML) applications reliant on corpora for training…

计算与语言 · 计算机科学 2024-11-08 Amin Abdedaiem , Abdelhalim Hafedh Dahou , Mohamed Amine Cheragui , Brigitte Mathiak

Talking-head videos constitute a predominant content type in real-time communication, yet publicly available datasets for video processing research in this domain remain scarce and limited in signal fidelity. In this paper, we open-source a…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Babak Naderi , Ross Cutler

We present a novel human annotated dataset for evaluating the ability for visual-language models to generate both short and long descriptions for real-world video clips, termed DeVAn (Dense Video Annotation). The dataset contains 8.5K…

计算机视觉与模式识别 · 计算机科学 2024-08-12 Tingkai Liu , Yunzhe Tao , Haogeng Liu , Qihang Fan , Ding Zhou , Huaibo Huang , Ran He , Hongxia Yang

We present the Claire French Dialogue Dataset (CFDD), a resource created by members of LINAGORA Labs in the context of the OpenLLM France initiative. CFDD is a corpus containing roughly 160 million words from transcripts and stage plays in…

计算与语言 · 计算机科学 2023-11-29 Julie Hunter , Jérôme Louradour , Virgile Rennard , Ismaïl Harrando , Guokan Shang , Jean-Pierre Lorré

Separating target speech from mixed signals containing flexible speaker quantities presents a challenging task. While existing methods demonstrate strong separation performance and noise robustness, they predominantly assume prior knowledge…

音频与语音处理 · 电气工程与系统科学 2025-07-18 Daning Zhang , Ying Wei