Fact · Speech recognition

The paper says most speech recognition systems used hidden Markov models to handle the timing of speech, and Gaussian mixture models to score how well each HMM state fits a short window of acoustic input.

Checked against its source on October 17, 2026

In the source's own words

“speech recognition systems use hidden Markov models (HMMs) to deal with the temporal variability of speech and Gaussian mixture models (GMMs) to determine how well each state of each HMM fits a frame or a short window of frames of coefficients that represents the acoustic input.”

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 acoustic model of the classic hybrid pipeline: a statistical timing model wrapped around a per-frame scorer. The scorer is the part that neural networks replaced.
What it does not show: A description of the field in 2012 as the authors saw it. Some systems before then already used neural networks, so the statement is about the majority, not all systems.

Source

Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsPeer-reviewed research · Geoffrey Hinton et al., IEEE Signal Processing Magazine, 2012

Cited on

Fact · Speech recognition

The paper says most speech recognition systems used hidden Markov models to handle the timing of speech, and Gaussian mixture models to score how well each HMM state fits a short window of acoustic input.

Checked against its source on October 17, 2026

In the source's own words

“speech recognition systems use hidden Markov models (HMMs) to deal with the temporal variability of speech and Gaussian mixture models (GMMs) to determine how well each state of each HMM fits a frame or a short window of frames of coefficients that represents the acoustic input.”

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 acoustic model of the classic hybrid pipeline: a statistical timing model wrapped around a per-frame scorer. The scorer is the part that neural networks replaced.
What it does not show: A description of the field in 2012 as the authors saw it. Some systems before then already used neural networks, so the statement is about the majority, not all systems.

Source

Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsPeer-reviewed research · Geoffrey Hinton et al., IEEE Signal Processing Magazine, 2012