Unverified50% confidenceFactExact time
Conformer is a hybrid neural network architecture proposed by Google in 2020, specifically designed for speech recognition tasks.
1
Sources
50%
Confidence
Long-term
Relevance
9/8/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedConformer 系列由 Google 于 2020 年提出，将自注意力的全局建模能力与深度可分离卷积的局部特征提取能力相结合，在 LibriSpeech 基准上曾创下 SOTA78% similarUnverifiedConformer（Convolution-augmented Transformer）架构由Google在2020年提出，结合了Transformer的全局自注意力机制和卷积神经网络的局部特征提取能力77% similarVerifiedThe Mixture of Experts (MoE) architecture was scaled up within the Transformer framework by Google Brain in 2017; its core idea is to group model parameters into multiple expert sub-networks, with only a small subset activated during each inference.64% 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62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/879156API
curl https://kongchang.com/api/v1/knowledge/claims/879156MCP
get_claim(id=879156)