Unverified50% confidenceFactExact time
d-vector was proposed by Google, extracting features frame by frame using a deep neural network followed by average pooling; x-vector was developed by Johns Hopkins University, based on a time-delay neural network with a statistical pooling layer introduced.
1
Sources
50%
Confidence
Long-term
Relevance
7/23/2026
First Seen
Sources
Related Claims
VerifiedIn 2017, Google published the paper 'Outrageously Large Neural Networks,' which propelled the MoE architecture into prominence in the field of deep learning.66% similarUnverified神经网络架构搜索（NAS）自2017年由谷歌提出以来已成为深度学习研究的重要分支65% similarUnverifiedGoogle Brain团队2012年发表了DNN-HMM混合模型，代表深度神经网络语音识别系统65% similarUnverifiedThe revival of modern MoE can be traced back to the 2017 paper published by the Google Brain team, 'Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer,' which was the first to integrate sparse MoE layers into large sequence models.65% similarUnverifiedIn 2011, Andrew Ng created the Google Brain project at Google, which used 16,000 CPU cores to build a deep neural network that successfully achieved unsupervised learning to recognize images of cats63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/600749API
curl https://kongchang.com/api/v1/knowledge/claims/600749MCP
get_claim(id=600749)