IDEAL Group Projects in Support of Individuals who are Deaf, Late-Deafened, or Hard-of-Hearing
uCaption® Generation II – Migration of uCaption® to Google’s Firebase Infrastructure
Year(s) Developed:
2018-2019
Objective:
The objective of developing uCaption is to provide an alternative to professional CART services (and not replace) in situations where the use of professional CART services are not logistically, technically, or financially possible.
About:
uCaption, a real-time text-streaming caption correction infrastructure and service, allows event participants (who have permission), to generate real time captions through the use of advanced speech to text (STT) technology. In addition, corrections can be made to captions in real-time. The corrections will be seen instantly by everyone viewing the captions, both locally and remotely. This will make highly accurate, low-cost, captioning services available as an alternative to professional CART services in situations where the use of professional CART services are not logistically possible, technically possible, or affordable.
Issues Addressed by uCaption:
Hundreds-of-millions of people worldwide, who are deaf, deaf-blind, or hard-of-hearing are being disenfranchised because events they wish to participate in are not live captioned. Forty eight million Americans have a significant hearing or a combined hearing/vision loss. Almost 900 million worldwide have some degree of hearing loss. Two thirds of the world’s deaf and hard of hearing population reside in developing countries.
Compatible Languages:
Afrikaans, Amharic, Arabic, Armenian, Azerbaijani, Basque, Bengali, Bulgarian, Catalan, Chinese (Cantonese), Chinese (Mandarin), Croatian, Czech, Danish, Dutch, English, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Javanese, Kannada, Khmer, Korean, Lao, Latvian, Lithuanian, Malay, Malayalam, Marathi, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Sinhala, Slovak, Slovenian, Spanish, Sundanese, Swahili, Swedish, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu, Vietnamese, and Zulu.
Additional Information:
Funding Organization:
Google Foundation
Project Partners:
TDI (formally known as Telecommunications for the Deaf and Hard of Hearing, Inc.)
———-
Speech2RTT® Communicator
Year(s) Developed:
2015-2017
Objective:
The objective of developing Speech2RTT was to enable people who are deaf, hard of hearing, and non-verbal to communicate with anyone, including people who can hear and speak, using their Android smart phone. Speech2RTT works across all wireless networks. It transcribes and then streams the text of what is being said, in real-time, between individuals. If a user cannot speak, or opts not to speak, they can type what they want to say, in real-time. Speech2RTT is available on Google Play and accommodates transcribing any one of 68 languages for users in 94 countries . Communications are 100% private. No live communications assistants (CAs) are involved… and no limits are imposed on the length of a communication.
Compatible Languages:
Afrikaans, Amharic, Arabic, Armenian, Azerbaijani, Basque, Bengali, Bulgarian, Catalan, Chinese (Cantonese), Chinese (Mandarin), Croatian, Czech, Danish, Dutch, English, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Javanese, Kannada, Khmer, Korean, Lao, Latvian, Lithuanian, Malay, Malayalam, Marathi, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Sinhala, Slovak, Slovenian, Spanish, Sundanese, Swahili, Swedish, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu, Vietnamese, and Zulu.
Benefits:
- Enables people who are deaf, hard of hearing, and non-verbal to communicate with anyone – using their Android smart phone;
- Works over all cellular networks;
- Transcribes speech to text, in real-time, in 68 languages;
- Communications are 100% private. No communications assistants (CAs) are involved;
- No limits are imposed on the length of communications;
- Offered at no cost until October 1, 2018, at which time a $12 annual fee will be assessed for continued use;
- Offers 24×7 availability with absolutely no waiting time;
- Enables users to communicate “on the go” since it is a mobile app;
- Fast communications: less than 300 ms latency streaming from one device to another; and,
- No voice-training is needed, even with accents;
Additional Information:
Funding Agencies:
National Institute on Disability, Independent Living, and Rehabilitation Research
Administration for Community Living
U.S. Department of Health and Human Services
Project Partner:
LiveWell Rehabilitation Research Center for Information and Communications Technology Access (ICT) Access
———-
uCaption® Generation I
Year(s) Developed:
2016-2017
Objective:
The objective of developing uCaption is to provide an alternative to professional CART services (and not replace) in situations where the use of professional CART services are not logistically, technically, or financially possible.
About:
uCaption, a real-time text-streaming caption correction infrastructure and service, allows event participants (who have permission), to generate real time captions through the use of advanced speech to text (STT) technology. In addition, corrections can be made to captions in real-time. The corrections will be seen instantly by everyone viewing the captions, both locally and remotely. This will make highly accurate, low-cost, captioning services available as an alternative to professional CART services in situations where the use of professional CART services are not logistically possible, technically possible, or affordable.
Issues Addressed by uCaption:
Hundreds-of-millions of people worldwide, who are deaf, deaf-blind, or hard-of-hearing are being disenfranchised because events they wish to participate in are not live captioned. Forty eight million Americans have a significant hearing or a combined hearing/vision loss. Almost 900 million worldwide have some degree of hearing loss. Two thirds of the world’s deaf and hard of hearing population reside in developing countries.
Compatible Languages:
Afrikaans, Amharic, Arabic, Armenian, Azerbaijani, Basque, Bengali, Bulgarian, Catalan, Chinese (Cantonese), Chinese (Mandarin), Croatian, Czech, Danish, Dutch, English, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Javanese, Kannada, Khmer, Korean, Lao, Latvian, Lithuanian, Malay, Malayalam, Marathi, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Sinhala, Slovak, Slovenian, Spanish, Sundanese, Swahili, Swedish, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu, Vietnamese, and Zulu.
Additional Information:
Funding Organization:
Google Foundation
Project Partner:
TDI (formally known as Telecommunications for the Deaf and Hard of Hearing, Inc.)
———-
IDEAL VoiceBase Captioning Infrastructure
Year(s) Developed:
2016-2017
Objectives:
to provide users the ability to upload audio recordings and uncaptioned /poorly captioned videos for automatic captioning. The system is capable of transcribing speech in any of the following languages/dialects: Dutch, English (Australian), English (Indian) , English (South East Asian), English (UK), English (US), French, German, Italian, Spanish, and Spanish (Latin American). The following formats are accepted: 3gp, aac, aiff, amr, asf, au, avi, caf, cf, flac, flv, m4a, m4v, mov, mp3, mp4, mpeg, mpg, ogg, ra, wav, webm, wma, and wmv. Audio recordings/videos are automatically captioned using neural networks and a highly sophisticated base of human speech recognition algorithms. The captions are then returned to the user in a time-coded editor that enables them (or someone else) to easily edit the captions without throwing off the timing of the captions.
Compatible Languages:
Dutch, English, French, German, Italian, Portuguese, and Spanish.
Funding Agency:
National Archives – National Historical Publications & Records Commission
Project Partners:
CRIS Radio
Connecticut State Library
———-
IDEAL Captions®
Year(s) Developed:
2013-2015
Objective:
The objective in developing IDEAL Captions was to provide a fully accessible, real time, captioning infrastructure in support of people who are hard of hearing or deaf.
Compatible Languages:
Afrikaans, Amharic, Arabic, Armenian, Azerbaijani, Basque, Bengali, Bulgarian, Catalan, Chinese (Cantonese), Chinese (Mandarin), Croatian, Czech, Danish, Dutch, English, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Javanese, Kannada, Khmer, Korean, Lao, Latvian, Lithuanian, Malay, Malayalam, Marathi, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Sinhala, Slovak, Slovenian, Spanish, Sundanese, Swahili, Swedish, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu, Vietnamese, and Zulu.
Additional Information:
Funding Agencies:
National Institute on Disability, Independent Living, and Rehabilitation Research
Administration for Community Living
U.S. Department of Health and Human Services
Project Partner:
Trace Research & Development Center | – University Of Maryland
———-
IDEAL 10-Band, High Definition, Voice Equalizer with Bone Conduction Technology
Year(s) Developed:
2013
Objective:
Develop and pair a graphics equalizer with powerful bone conduction technology to enable individuals with conductive hearing loss to hear more clearly. Note: Conductive Hearing Loss is due to problems with the ear canal, ear drum, or middle ear and its tiny bones.
Additional Information:
Funding Organization:
The Jacobs Family Trust
Project Partners:
MaxVirtual
2013 International Consumer Electronics Show
Eureka Park – 2013 CES
———-
IDEAL SubTube
Year(s) Developed:
2010
Objective:
Provide the ability to display one of multiple caption/subtitle video tracks, depending upon the language preference of the viewer.
Compatible Languages:
All/Any
Additional Information:
Funding Organization:
Google, Inc.
———-
Developed the first, Interactive, Video Communications Technology for Sign-Language Communications Over the Internet
Year(s) Developed:
1992-1994
Description:
In early 1994, Project Freedom’s / IDEAL’s work was commemorated in a video. The video captured the first two-way “voice telephone” ASL conversation. The conversation took place between students and teachers from the Horace Mann Montessori School in Dayton, Ohio. The video also showcased historical footage of Alexander Graham Bell. Although a competitor, Sprint used Project Freedom’s Vistium Video System hardware and infrastructure to conduct the first VRS pilot test in Texas. Here are a few marketing pieces from that time:
- Although a competitor, Sprint used our system for their pilot test in Texas:
http://www.ideal-group.org/initiatives/sprint.jpg - GA-SK Newsletter article about the Texas pilot:
http://www.ideal-group.org/initiatives/ga-sk.jpg. - Reid Huntt (Chairman of the FCC at the time) and Steve Jacobs demonstrating our video system to FCC Commissioners
http://www.ideal-group.org/initiatives/Reed_Hundt.jpg
Funding Organizations:
AT&T Project Freedom
AT&T Global Information Solutions
NCR Corporation
Bell Laboratories
