We don’t often highlight obituaries in this space, but we’re compelled to remember Frederick Jelinek, an electrical engineering professor who was crucial in creating the technology “that allows computers to interpret human speech and translate languages,” according to afinememorial in the Los Angeles Times, who died recently of a heart attack in his Johns Hopkins University office.

Jelinek’s vision and work “revolutionized the field,” said Sanjeev Khudanpur, associate professor of electrical engineering at Johns Hopkins. “Fifty years ago no one thought that was possible. Today, it's the dominant paradigm.”

Jelinek's application of statistical theory and probability to voice recognition was “a trailblazing approach that later was adapted to many other fields that employ artificial intelligence, including stock market prediction and biomedical research,” the Times wrote.

Working at IBM (News - Alert) Research and Johns Hopkins, Jelinek “led the way in developing the statistical theory behind modern voice-recognition systems,” the Times said: “Essentially, he helped turn a nascent science that merely transcribed human speech into a sophisticated one that could interpret meaning and anticipate what the speaker would say next.”

Born Nov. 18, 1932, to a Jewish father and Christian mother in Kladno in what is now the Czech Republic, Jelinek was barred from formal schooling by Nazi edict after he finished the second grade, the Times wrote, noting that “through much of World War II, he was educated in underground academies.” Jelinek's father died in the concentration camp at Terezin.

In 1949, the family moved to the United States where Jelinek earned a bachelor's degree at the Massachusetts Institute of Technology, as well as a master's degree and a doctorate. In 1957 he traveled to then-Czechoslovakia, where he met his future wife, Milena Tobolova, a filmmaker and dissident against the Communist government, according to Jelinek’s surviving son, William.

Frederick Jelinek studied applying information theory to linguistics, and taught information theory at Cornell University. He later worked for 21 years at IBM, heading a team “that sought to apply the power of supercomputers to the challenges of transcribing and translating the spoken word,” the Times said:

“Khudanpur said that previous efforts at voice recognition and translation focused on codifying rules and applying them — an approach that was frustrated by the complexity and subtlety of language. Jelinek's approach was to assemble a huge database of text and let the computer calculate the probabilities of words appearing in relation to other words — deriving meaning from context rather than rules.”

Jelinek retired from IBM in 1993 and was recruited by Johns Hopkins to head its Center for Language and Speech Processing.