Future computers that recognize the ways we express attitudes as well as words will enable much more sophisticated, user-friendly systems capable of understanding and participating in conversations
In the future, computers may be capable of talking to us during meetings just like a remote teleconference participant. But to help move this science-fiction-sounding goal a step closer to reality, it’s first necessary to teach computers to recognize not only the words we use but also the myriad meanings, subtleties and attitudes they can convey.
During the 168th Meeting of the Acoustical Society of America (ASA), to be held October 27-31, 2014, at the Indianapolis Marriott Downtown Hotel, Valerie Freeman, a Ph.D. candidate in the Department of Linguistics at the University of Washington (UW), and colleagues will describe their National Science Foundation-sponsored work for the Automatic Tagging and Recognition of Stance (ATAROS) project. The project’s goal is to train computers to recognize the various stances, opinions and attitudes that can be revealed by human speech.
“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? 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,” explained Freeman.
Identifying cues to “stance taking” in audio recordings of people talking is a good place to start searching for answers, according to Freeman and the principal investigators on the project, including Professors Gina-Anne Levow and Richard Wright in the Department of Linguistics, and Professor Mari Ostendorf in the Department of Electrical Engineering.
“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,” Freeman said.
Not too surprising? Maybe not in terms of heated arguments, but the researchers found the same patterns within ordinary conversations, too. “People talk faster and say more at once when they’re working on more engaging tasks such as balancing an imaginary budget as opposed to arranging items within an imaginary store,” Freeman noted.
The researchers’ also noticed that people also appear to be less fluent in the engaging tasks—displaying more false starts, cut-off words, “ums” and repetitions.
Further, it appears that “men might do this more than women—regardless of whether they’re talking to another man or a woman.” Freeman places a heavy emphasis on the word “might,” because to date they’ve only explored this particular lack of fluency with 24 people.
So far, for the entire project, the researchers have worked with and recorded a total of 68 people of varying ages and backgrounds, all from the Pacific Northwest.
“We plan to continue to analyze these conversations for subtler cues and more complex patterns—variations in pronunciations when comparing positive and negative opinions, men vs. women, and older vs. younger people,” said Freeman. “In the future, we hope to record people from other locations to see whether different regions have different ways of expressing the same opinions.”
The lessons learned from this work should help enable sophisticated speech recognition systems of the future. “Think of all of the amazing things the computer on Star Trek can do,” Freeman said. “To reach that level of sophistication, we need computers to understand all the subtle parts of a message—not just the words involved. 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.”
The Latest on: Voice recognition
[google_news title=”” keyword=”voice recognition” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Voice recognition
- The rise of Airchat & growing debate over navigating Internet with voice—through search, command or notes. Can it gain momentum?on April 27, 2024 at 10:51 am
Voice input technology faces challenges despite widespread adoption in internet products. Smart speaker shipments decline, while the voice recognition market is poised for significant growth. Users ...
- Shaver dies at 96, was radio voice for Minnesota North Starson April 27, 2024 at 6:22 am
Al Shaver, a media honoree in the Hockey Hall of Fame and longtime radio voice of the Minnesota North Stars, has died at the age of 96.
- Afghan Women Voice ‘Deep Disappointment’ and ‘Dread’ Over Potential Taliban Recognitionon April 26, 2024 at 11:59 pm
In a nationwide women’s consultation, Afghan women have expressed “dread” and “anxiety” over the potential international recognition of the de facto authorities (DFA), with 67 percent stating it would ...
- Tourist agency sponsoring Juneteenth speech conteston April 26, 2024 at 5:00 pm
The grant was awarded to Farrell schools to host a speech contest for students in three divisions. "We want the youth coming up to perfect their speaking skills and to reflect on Juneteenth," Peggy ...
- Get this Amartey party started: Swans forward finding his voiceon April 26, 2024 at 5:00 pm
He's starting to get that outside recognition, but inside the four walls there's no ... a languid disposition at times to those on the outside, but is not afraid to voice his thoughts in the Swans' ...
- Enhancing Cybersecurity Defenses: The role of Voice Cloning in Penetration Testingon April 26, 2024 at 2:00 am
By Alex Serdiuk, CEO, Respeecher Newer and more impactful technological advancements are making the quest for foolproof cybersecurity measures more critical than ever. As organizations are doing ...
- Speech and Voice Recognition Market Peak Potential Anticipating Market Size to Skyrocket in Futureon April 25, 2024 at 9:09 pm
report_id=bw1075 Speech and Voice Recognition Market is valued approximately at USD 12.3 Billion in 2019 and is anticipated to grow with a growth rate of more than 17.20 % over the forecast period ...
- Chico Police Department honors service and dedication at annual recognition ceremonyon April 25, 2024 at 5:31 pm
The Chico Police Department held its annual 'Of the Year' awards ceremony, on Thursday morning. The event was a celebration of the hard work and dedication of o ...
- MG’s Cyberster drop-top electric vehicle goes on sale in the UKon April 25, 2024 at 5:09 am
The Trophy comes with an electric motor that produces 335bhp, has a torque figure of 475Nm and can do 0-60mph in 4.8 seconds. The GT, meanwhile, comes with dual electric motors which boast a power ...
- Luxury off-road Mercedes EV features 360-degree spin feature plus plush interior and futuristic voice recognition systemon April 24, 2024 at 6:29 pm
MERCEDES-Benz has electrified the G-Wagon without cutting into its rich off-road identity and famous boxy appearance. A breakthrough in the fusion of tradition and technology, the ...
via Bing News