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
- Google does record your voice but there's a very simple way to stop iton May 10, 2024 at 4:33 am
"When you speak to Google services, Google uses its audio recognition technologies to process your audio ... to listening to snippets of saved audio which is then used to improve voice search. "For ...
- Smart Home Devices Market Surging with 17.8% CAGR: Rising Popularity of Voice-Controlled Technology | FMIon May 9, 2024 at 10:21 pm
The global smart home devices market is projected to have a CAGR of 17.8% during the forecast period. The current valuation of the smart home devices market is USD 58.4 Billion in 2023. The value of ...
- Philippines Voice Recognition System Market Update Companies Showing Sign of Enormous Growthon May 9, 2024 at 12:12 am
According to the latest research assessment of the Philippines Voice Recognition System Market by Report Ocean, there is a notable increase in growth opportunities projected for the forthcoming years.
- FinVolution to Hold 9th Global Data Science Competition, Focus on Deepfake Speech Detection in LLM eraon May 8, 2024 at 5:00 pm
The 9th FinVolution Global Data Science Competition targets deepfake speech detection, tackling the challenge of distinguishing between cloned and authentic voices in the LLM era. The contest is part ...
- Sperm whale speech — with ‘alphabet’ — is decoded. What other animals can AI translate?on May 8, 2024 at 3:25 pm
Researchers of chatty creatures like bats, bees, songbirds and whales gather many hours of sound or video recordings and then plug that data into AI language models, the way we might with tools like ...
- Lucas Systems Is More Than A Voice Vendor; It Is A Warehouse Optimization Solutionon May 8, 2024 at 7:02 am
Today, for many professionals, "WMS" is synonymous with "warehouse optimization." Lucas Systems, a provider of Voice Recognition solutions, also provides optimization.
- For American Jews, Biden’s Speech on Antisemitism Offers Recognition and Healingon May 7, 2024 at 6:26 pm
While his message resonated with many Jewish leaders, the president’s remarks drew criticism from Republicans and supporters of Palestinians on the left.
- ElevenLabs Is Building an Army of Voice Cloneson May 6, 2024 at 8:52 am
A tiny start-up has made some of the most convincing AI voices. Are its creators ready for the chaos they’re unleashing?
- Speech recognition market to reach $54bn by 2030 – Reporton May 4, 2024 at 8:01 pm
The global voice and speech recognition market is expected to reach $53.67bn by 2030, growing at a compound annual growth ...
- NVIDIA ChatRTX updated: new models, voice recognition, media search, and more with AIon May 1, 2024 at 7:36 pm
NVIDIA updates its ChatRTX AI chatbot, with improved LLM support, image search, speech recognition and more for localized AI goodness.
via Bing News