Geoffrey E. Hinton, Li Deng, Dong Yu, George E. Dahl, Abdelrahman Mohamed, Navdeep Jaitly, Andrew Senior, Vincent Vanhoucke, Patrick Nguyen, Tara N. Sainath, Brian Kingsbury · IEEE Signal Processing Magazine 2012 · 2012
DOI: 10.1109/msp.2012.2205597
Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).
Most current 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. An alternative way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) 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. This article provides an overview of this progress and represents the shared views of four research groups that have had recent successes in using DNNs for acoustic modeling in speech recognition.
· 1905 citations
Last synced
Computation 2026 · 0 citations
Journal of the Chinese Institute of Engineers 2026 · 0 citations
Journal of Signal Processing 2026 · 0 citations
International Journal of Engineering Science and Information Technology 2026 · 0 citations
No comments yet — start the discussion below.