Artificial intelligence · 1975

Statistical speech recognition

Hidden Markov models turn speech recognition into a probability problem.

James Baker's DRAGON system and Fred Jelinek's group at IBM applied hidden Markov models to recognising speech in the mid-1970s. Jelinek's data-driven approach beat hand-written linguistic rules and dominated speech recognition until deep learning.

See it in the living tree Wikipedia

Arcs above join it to what it stood on, arcs below to what it led to. The bar places this stretch on the tree's whole timeline.

What it built on 2

Information theory 1948
Bayes' theorem 1763

What it led to 3

Statistical machine translation 1990
Siri 2011
Deep speech recognition 2012

Related measurements

The dashed line marks when it first worked.

Training compute of notable AI models Source: Epoch AI, Notable AI Models (CC BY 4.0)

Computation per constant dollar, 1850-2006 Latest: 7.3B million units of computer power per 2006 $ (2003) Source: Nordhaus 2007, Two Centuries of Productivity Growth in Computing, J. Econ. Hist. 67(1), Table 6