The software on your smartphone may be able to recognize your voice, but it probably can't pick up nuances like sarcasm or outrage. But research on how to detect opinions and attitudes in everyday speech could enable tomorrow's computers to pick up on these subtle cues.
The research aims to address some conundrums about verbal and textual communication. Why is it easy to communicate an attitude while speaking, but not necessarily by typing the same statement? How can the same words send different messages? These are the types of questions the Automatic Tagging and Recognition of Stance (ATAROS) project aims to answer.
"Think of all of the amazing things the computer on 'Star Trek' can do," Valerie Freeman, a linguistics researcher at the University of Washington, said in a statement. "To reach that level of sophistication, we need computers to understand all the subtle parts of a message — not just the words involved." [Science Fact or Fiction? The Plausibility of 10 Sci-Fi Concepts]
Freeman and her colleagues presented the research Tuesday (Oct. 28) at the 168th meeting of the Acoustical Society of America (ASA) in Indianapolis, Indiana.
In their study, the researchers recorded the voices of 68 people of different ages and backgrounds, all from the Pacific Northwest. They were listening for cues that could reveal the speaker's stance on a topic.
The researchers found that when pairs of people worked together on various tasks, they tended to speak faster, louder and with "more exaggerated pitches" when they had a strong opinion than when they had a weak one. This was true even though these were regular conversations, not arguments, the researchers said.
For example, people talked more quickly when they worked on more engaging tasks, such as balancing an imaginary budget, as opposed to less complicated tasks like arranging items within an imaginary store, Freeman said.
In addition, when people were engaged in a subject, they spoke less fluently, the researchers found. They tended to speak in false starts, repeat themselves and say "um" more often than when they were less interested in the topic of conversation.
Freeman said that men appear to show this lack of fluency more often than women, but she cautioned that this part of the study was based on data from only 24 people.
In the future, the researchers plan to continue analyzing the conversations for subtler cues and patterns, such as different pronunciations for positive versus negative opinions, men versus women and older people versus younger people. The scientists also hope to record people from different places, who may express the same opinions in different ways, the researchers said.