Navigation Links
Research aims to improve speech recognition software
Date:8/11/2010

BINGHAMTON, NY Anyone who has used an automated airline reservation system has experienced the promise and the frustration inherent in today's automatic speech recognition technology. When it works, the computer "understands" that you want to book a flight to Austin rather than Boston, for example. Research conducted by Binghamton University's Stephen Zahorian aims to improve the accuracy of such programs.

Zahorian, a professor of electrical and computer engineering, recently received a grant of nearly half a million dollars from the Air Force Office of Scientific Research. The funds will support the two-year development of a multi-language, multi-speaker audio database that will be available for spoken-language processing research. Zahorian and his team plan to gather and annotate recordings of several hundred speakers each in English, Spanish and Mandarin Chinese.

"The challenge," he said, "is to get speech recognition working better in real-life situations."

That's why the samples in the new database will come from publicly available sources such as YouTube.

Zahorian's team will annotate each sample, creating a more detailed version of closed captioning, including time stamps and descriptions of background sounds. Once the human listener has finished with the transcription, automatic speech recognition algorithms will be used to align the recording with the captions. Next, software will be developed to verify and correct errors in the time alignment.

"Speech-recognition algorithms begin by mimicking what your ear does," Zahorian said. "But we want the algorithms to extract just the most useful characteristics of the speech, not all of the possible data. That's because more detail can actually hurt performance, past a certain point."

The field of automatic speech recognition has a long history, dating back to projects at Bell Labs before the computer age. These days, much of the technology relies on algorithms that convert sounds into numbers.

In Zahorian's research, he represents speech as a picture in a time-frequency plane. He then uses image-processing techniques to extract features of the speech, which has led him to focus more on time than on frequency.

When researchers are ready to test an algorithm, they rely on a common set of databases held by the Linguistic Data Consortium. Zahorian's unusual image-based approach has given his team some of the best results ever reported for automatic speech recognition experiments using two of the consortium's best-known databases.

The database Zahorian develops with the new funding will join these others, offering researchers around the world a new way to test their theories with samples of real-life speech.

Some mistakes are inevitable, given the variations in pitch, tone and pronunciation from person to person.

Still, the field does have a clear standard, Zahorian said: "In order to be useful, a system should have a word-error rate of no more than 10 percent."

Zahorian is interested in language modeling if someone has said these three words, what's the fourth word likely to be? as well as conversation modeling that is, predicting when the speakers will switch. He's also intrigued by the potential to make advances by using established methods from other fields, including the neural networks developed by researchers working in artificial intelligence.

He sees a future in which automatic speech recognition will enable technology to extract the meaning of speech as well as the words.

"The dream," Zahorian said, "is that someday travelers will be able to speak into a little gadget that will translate what they've said into another language instantly and accurately."


'/>"/>

Contact: Gail Glover
gglover@binghamton.edu
607-777-2174
Binghamton University
Source:Eurekalert  

Related medicine news :

1. Embedded Mobile & M2M Device revenues to Rise to Almost $19 Billion Globally by 2014, Says Juniper Research
2. 2010 HSR Impact Award recognizes surgical safety research
3. MSU launches first anti-counterfeiting research program
4. Researchers map all the fragile sites of the yeast Saccharomyces cerevisiaes genome
5. UH Case Medical Center researchers publish promising findings for advanced cervical cancer
6. Researchers discover new way to kill pediatric brain tumors
7. Family Research Council: Planned Parenthood Report Oversexualizes Ten-Year-Olds, Undermines Parental Authority
8. Michael J. Fox Foundation Awards $1 Million to Drive Critical New Research Tools and Technologies in Parkinsons Drug Development
9. Luth Researchs IndicatorEDG(TM) Study Finds Americans Hopes of Achieving Their Dreams Are Fading
10. International Diabetes Federation awards $2 million to 9 global diabetes research projects
11. Gladstones Robert Mahley to receive Research!America advocacy award
Post Your Comments:
*Name:
*Comment:
*Email:
Related Image:
Research aims to improve speech recognition software
(Date:10/13/2017)... (PRWEB) , ... October 13, 2017 , ... Apple ... care services, staged a mock evacuation of the facility as part of a disaster ... Fire Department, Echo Hose EMS and Shelton City Emergency Manager, as well as the ...
(Date:10/13/2017)... , ... October 13, 2017 , ... Global Healthcare Management’s ... Alexandria Park in Milford, NJ. This free event, sponsored by Global Healthcare Management’s ... The fun run is geared towards children of all ages; it is a ...
(Date:10/13/2017)... ... October 13, 2017 , ... “The Journey: From the ... danger possible to save lost souls in the Philippines. “The Journey: From the Mountains ... a dedicated teacher of the Bible. She has taught all ages and currently teaches ...
(Date:10/12/2017)... ... October 12, 2017 , ... Planet Fitness, one of the largest and ... plans to open a flagship location in Covington, LA at 401 N. U.S. Highway ... store next to Office Depot in the Holiday Square shopping center. Its location allows ...
(Date:10/12/2017)... ... 2017 , ... Asante, a nationally recognized health system in ... existing home health joint venture through an agreement, effective October 1, 2017, to ... home health company with Asante, delivering clinically integrated care, for the past eight ...
Breaking Medicine News(10 mins):
(Date:10/10/2017)... -- NDS received FDA 510(k) clearance in May 2017 for its highly ... designed for endoscopy environments. An innovative secondary monitor solution, ZeroWire ... support the improvement of patient outcomes, procedural efficiency, and the lowering ... ... ...
(Date:10/4/2017)... 4, 2017  South Korean-based healthcare product Development Company ... "cprCUBE" on Kickstarter. The device will educate the user ... with better efficiency compared to the dated and pricey ... on efficacy of the compression for a more informed ... goal to raise $5,000. ...
(Date:10/2/2017)... 2017  Eli Lilly and Company (NYSE: ... third quarter of 2017 on Tuesday, October 24, 2017. ... day with the investment community and media to further ... call will begin at 9 a.m. Eastern time. Investors, ... webcast of the conference call through a link that ...
Breaking Medicine Technology: