Fact · Speech recognition
The authors write that deep neural networks with many hidden layers, trained with new methods, have been shown to outperform Gaussian mixture models on a variety of speech recognition benchmarks.
Checked against its source on October 17, 2026
In the source's own words
“that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition benchmarks, sometimes by a large margin.”
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups, Geoffrey Hinton et al., IEEE Signal Processing Magazine, 2012, Opening paragraph.
Open the original (DOI 10.1109/MSP.2012.2205597)- What it measures
- This is the result that moved the field from Gaussian mixtures to neural acoustic models, starting around 2012. The neural network in this setup still sat inside the older HMM pipeline.
- What it does not show
- The margin varied by benchmark, and the statement is a summary by the authors, not a single number. The paper is a review of work from several groups.