Deep Neural Networks for Acoustic Modeling in Speech

Editorial record

Plain-language summary

In a speech recognizer the acoustic model estimates how likely each short audio frame corresponds to each sub-phonetic state; the paper describes replacing the standard Gaussian-mixture estimator with a deep neural network that takes several frames of audio features and outputs those state probabilities, often pretrained layer by layer and then fine-tuned. Reported jointly by teams at Microsoft, Google, IBM, and the University of Toronto, the deep networks lowered word error rates on multiple large-vocabulary benchmarks. The shared results gave the field consistent evidence that deep acoustic models were a general improvement, and they were adopted in commercial speech systems.