Researchers from the Department of Linguistics at the University of Washington (UW) in the U.S are leading a project called the Automatic Tagging and Recognition of Stance or ATAROS.

The ATAROS project aims to teach computers how to recognize natural human speech used in everyday communication. Human speech encompasses stances, opinions and attitudes.

Like Us on Facebook

"What is it about the way we talk that makes our attitude clear while speaking the words, but not necessarily when we type the same thing?" asked Valerie Freeman, a Ph.D. candidate at the university.

"How do people manage to send different messages while using the same words? These are the types of questions the ATAROS project seeks to answer,"

Freeman said the best way to start is to record people's conversations and observe their speech behavior.

"In our recordings of pairs of people working together to complete different tasks, we've found they tend to talk faster, louder and with more exaggerated pitches when expressing strong opinions as opposed to weak opinions," said Freeman.

Researchers found the same pattern appear in ordinary conversations. They also noticed people appear less fluent when performing certain tasks.

The study hopes to enable future computer systems to recognize human speech and respond accordingly.

"To reach that level of sophistication, we need computers to understand all the subtle parts of a message -- not just the words involved." Freeman added.

"Projects like ATAROS are working to help computers learn how to figure out what people really mean when they speak, so that in the future computers will be capable of responding in a much more 'human-like' manner."

Researchers at the university plan to discuss the project at the 168th Acoustical Society of America (ASA) meeting from Oct. 27 to Oct. 31.

TagsVoice Recognition, Automatic Tagging anf Recognition of Stance, ATAROS project, University of Washington, Department of Linguistics, Human Speech, 168th Acoustical Society of America, ASA