Forum Posts

Md. Asaduzzaman
Apr 04, 2022
In Welcome to the Forum
Programmers and engineers have made great strides in the science of speech recognition over the past decade, so you'd be forgiven for thinking this technology is a relatively new development. Much of the reporting and scholarship around voice recognition technology focuses solely on the era of Siri after 2011, after the release of Apple's now ubiquitous personal assistant. But voice recognition technology has a rich secret history dating back to the mid-twentieth century, when crude computers had to fill an entire warehouse with vacuum tubes and diodes just to solve a simple equation. And this story not only reveals interesting anecdotes about the technology we know and love today, it also points the way to potential future breakthroughs in the field. Let's explore the untold history of voice recognition technology and see how much progress has been made over the years (and how much has stayed the same). AUDREY and the shoebox At the beginning of the 20th century, the American research company Bell Laboratories (named after its founder Alexander Graham Bell, the inventor of the telephone) accumulated a series of impressive technological advances: the invention of radio astronomy (1931), the solar cells (1941), and transistors (1947). Then, in 1952, Bell Labs marked another revolutionary technological advance: the AUDREY system, a set of vacuum tube circuits housed in a six-foot-tall relay rack that could understand the numerical digits spoken into its high- speaker. When matched to a specific voice, AUDREY can accurately interpret over 97% of the numbers spoken to her. AUDREY is undoubtedly primitive by today's standards, but it laid the Employee Email Database foundation for voice dialing, a technology widely used by toll line operators. (You remember ?)Ten years later, IBM unveiled its Shoebox machine at the 1962 World's Fair in Seattle. Like AUDREY, Shoebox could understand up to 16 words, including the numbers 0 through 9. And when Shoebox heard a number combined with a command word (like "plus" or "total"), he would then ask a machine to calculate linked to calculate and print the answer to simple arithmetic problems. Just like that, the world's first voice recognition calculator was born! HARPY takes flight Speech recognition began to take off in the 1970s, largely due to interest and funding from the US Department of Defense and DARPA. Running from 1971 to 1976, DARPA's Speech Understanding Research (SUR) program was one of the largest research initiatives ever undertaken in the field of speech recognition. SUR eventually helped create Carnegie Mellon's "HARPY" speech recognition system, capable of processing and understanding over 1,000 words. HARPY was particularly important because of its use of "beam search" technology, which was a much more efficient method for machines to retrieve the meaning of words from a database and better determine sentence structure. Spoken. Indeed, advances in voice recognition have always been closely tied to similar advances in search engine technology – look no further than Google's current dominance in both areas for proof of this.
0
0
2

Md. Asaduzzaman

More actions