Prehistory — From Neural Networks to the TransformerGeoffrey Hinton, Li Deng, Dong Yu et al. (University of Toronto, Microsoft, Google, IBM)Geoffrey HintonUniversity of TorontoMicrosoftGoogleIBM

Deep Neural Networks for Acoustic Modeling in Speech Recognition

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

Deep Neural Networks for Acoustic Modeling in Speech Recognition — a joint review by four research groups

Why it matters

Separate industry groups confirmed the same shift (HMM→DNN), and deep learning became the industry standard for speech recognition

Source — Primary sources first; secondary reports are labelled “Press”

Officialresearch.googlehttps://research.google/pubs/deep-neural-networks-for-acoustic-modeling-in-speech-recognition/

Added in Week 35, 2026 · See that week

On the map — ⓪ Prehistory line

  1. Previous stopImageNet
  2. This recordDeep Neural Networks for Acoustic Modeling in Speech Recognition
  3. Next stopAlexNet
See it on the map

Nearby on the same axis

Building high-level features using large scale unsupervised learningPaperMulti-column deep neural network beats humans with 99.46% at IJCNN 2011 GTSRBOfficialRepresentation Learning: A Review and New PerspectivesPaperImproving neural networks by preventing co-adaptation of feature detectorsPaper