1,394 research outputs found
N20EM dataset for multimodal lyric transcription
N20EM dataset for multimodal lyric transcription, proposed in our ACM MM 2022 paper, MM-ALT: A Multimodal Automatic Lyric Transcription System. This dataset contains recordings of three modalities: audio, video, and IMU motion signal.
Our paper's camera ready version: https://arxiv.org/abs/2207.06127
Project website: https://n20em.github.io/
Please cite our work as:
@inproceedings{gu2022mm,
title={MM-ALT: A multimodal automatic lyric transcription system},
author={Gu, Xiangming and Ou, Longshen and Ong, Danielle and Wang, Ye},
booktitle={Proceedings of the 30th ACM International Conference on Multimedia},
pages={3328--3337},
year={2022}
}Add data for VAD training and accompaniment of each utterance
N20EMv2 dataset for automatic music transcription from multimodal singing
<p>N20EMv2 dataset for multimodal automatic music transcription from multimodal singing, presented in our TOMM 2024 paper, Automatic Lyric Transcription and Automatic Music Transcription from Multimodal Singing. This dataset contains recordings of two modalities: audio and video. </p>
<p>Our paper is available at: https://dl.acm.org/doi/10.1145/3651310.</p>
<p>Code is available at: https://github.com/guxm2021/SVT_SpeechBrain</p>
<p>Please cite our work as:</p>
<pre>@article{gu2024automatic,
title={Automatic Lyric Transcription and Automatic Music Transcription from Multimodal Singing},
author={Gu, Xiangming and Ou, Longshen and Zeng, Wei and Zhang, Jianan and Wong, Nicholas and Wang, Ye},
journal={ACM Transactions on Multimedia Computing, Communications and Applications},
publisher={ACM New York, NY},
year={2024}
}</pre>
China’s Belt and Road Initiative: An Epochal Initiative Connecting the World
In 2013, the Chinese Government launched the Belt and Road Initiative (BRI), a massive global infrastructure-building initiative, to increase trade by connecting cities within and across continents. The initiative is redefining globalisation, urbanisation, regionalism, and development. Professor Xiangming Chen has released a policy expo-book (sponsored by the Regional Studies Association) that traces out the changing economic, social, and spatial fortunes of the regions connected to the initiative. In this timely book, the author outlines a modern, fresh and factual account of an outward-looking China ushering in a new era of globalisation through a variety of widespread and far-reaching trans-boundary economic and infrastructure connectivities
Joint optimization of service function chaining and resource allocation in network function virtualization
Cost-efficient vehicular crowdsensing based on implicit relation aware graph attention networks
sj-jpg-1-imr-10.1177_03000605221105368 - Supplemental material for Pralsetinib treatment for multiple <i>RET</i> fusions in lung adenocarcinoma: a case report
Supplemental material, sj-jpg-1-imr-10.1177_03000605221105368 for Pralsetinib treatment for multiple RET fusions in lung adenocarcinoma: a case report by Xiangming Cao, Xiongwei Liu, Simin Wang, Zhen Liu, Xin Ren, Debin Sun and Lichun Deng in Journal of International Medical Research</p
An SDN/NFV based framework for management and deployment of service based 5G core network
- …
