Experiment shows smartphone speech recognition faster than typing

SAN FRANCISCO - Results from an experiment suggest that speech recognition, in case of composing text messages on smartphone, can be faster and more accurately than humans can type on phone screens. "They grew up texting, so we're putting speech recognition up against people who are really good at this task," James Landay, a professor of computer science at Stanford and co-author of the new study published online at arXiv.org, was quoted as saying in a news release from Stanford on Wednesday. The results: for English, speech recognition was three times faster than typing, and the error rate was 20.4 percent lower; in Mandarin Chinese, speech was 2.8 times faster, with an error rate 63.4 percent lower than typing. "We knew speech recognition is pretty good, so we expected it to be faster, but we were actually quite surprised to find that it was almost three times faster than typing on a keyboard," said co-author Sherry Ruan, a computer science PhD student at Stanford who helped run the experiments. Although only the speech recognition software from Baidu, a web services company headquartered in Beijing, China, and listed on NASDAQ Stock Market in New York, the United States, was used, the researchers suspect that other high-accuracy speech engines perform at a similar level and they hope that given the results of their experiment, engineers will be encouraged to design user interfaces that take better advantage of the speech recognition technology.