J
Jingsong Wang
Researcher at Paradigm
Publications - 5
Citations - 13
Jingsong Wang is an academic researcher from Paradigm. The author has contributed to research in topics: Process (engineering) & Task (project management). The author has an hindex of 1, co-authored 5 publications receiving 11 citations.
Papers
More filters
AutoDL Challenge Design and Beta Tests-Towards automatic deep learning
Zhengying Liu,Olivier Bousquet,André Elisseeff,Sergio Escalera,Isabelle Guyon,Julio C. S. Jacques,Adrien Pavao,Danny Silver,Lisheng Sun-Hosoya,Sebastien Treguer,Wei-Wei Tu,Jingsong Wang,Quanming Yao +12 more
TL;DR: The challenge protocol and baseline results are presented to seek community feed-back and drive the community to work on finding fully automatic ways of designing DL models.
Posted Content
AutoSpeech 2020: The Second Automated Machine Learning Challenge for Speech Classification
TL;DR: The challenge is outlined, the competition protocol, datasets, evaluation metric, starting kit, and baseline systems are described and every submitted solution should contain an adaptation routine which adapts the system to the new task.
Proceedings ArticleDOI
AutoSpeech 2020: The Second Automated Machine Learning Challenge for Speech Classification.
TL;DR: The AutoSpeech challenge as discussed by the authors is a challenge for automated machine learning (AutoML) solutions to automate the process of applying machine learning to speech processing tasks, which includes speech tasks, noisier data in each task, and a modified evaluation metric.
Proceedings ArticleDOI
Auto-KWS 2021 Challenge: Task, Datasets, and Baselines
TL;DR: The Auto-KWS 2019 challenge as discussed by the authors has focused on the problem of customized keyword spotting, where the target device can only be awakened by an enrolled speaker with his specified keyword and the speaker can use any language and accent to define his keyword.
Posted Content
Auto-KWS 2021 Challenge: Task, Datasets, and Baselines
TL;DR: The Auto-KWS 2019 challenge as discussed by the authors has focused on the problem of customized keyword spotting, where the target device can only be awakened by an enrolled speaker with his specified keyword and the speaker can use any language and accent to define his keyword.