HP SpeechBot Experimental index of popular US radio shows, based on speech recognition technology at Compaq.com. http://speechbot.research.compaq.com/
Extractions: HP Labs All of HP US Research News and events Technical reports ... Downloads Search for: Topics: All Topics Current Events Music Personal Investment Sports Talk Dates: All dates In the last 3 days In the last week In the last 2 weeks In the last month In the last 3 months In the last 6 months In the last year Tip: To improve the relevance of your results, enter more than one word in the " Search for " box SpeechBot listed below Note: Transcripts of the content based on speech recognition are not exact. SpeechBot currently indexes 15321 hours of content from the following websites: Fresh Air American RadioWorks Here and Now On Point PBS Online NewsHour ... U.S. Department of Defense Briefings Soundcheck Marketplace Radio Business News Motley Fool Radio Show Only A Game Scuba Radio Car Talk Radio Show Public Interest The Brian Lehrer Show The Charlie Rose Show ... Feedback to HP Labs
About Virtual Hold Technology Innovative IVR callback software which uses speech recognition to schedule a live person call back rather than having customer wait in the on hold queue forever. Also includes ability to post a return call time meter to customer's browser. http://www.virtualhold.com
Extractions: - Genesys and Virtual Hold Technology to Jointly Market and Deliver Virtual Queuing Solution Globally Click here - AEGON insurance company selects Virtual Hold to improve customer service and lower operating expenses. - Virtual Hold releases Version 5.4.1 containing new features and new adapters. - Cincinnati Bell Chooses Virtual Hold Queue Management solution. Click here - Utilities across the nation rely on Virtual Hold for queue management. Click here About Us
Buffalo Hearing And Speech Center - Home Page Tests, evaluates and treats children and adults with hearing loss and speech problems. Information on advanced technology hearing aids, assistance devices and repairs provided. http://www.bflohearspeech.org/
Extractions: Skip navigation document library contact us sitemap search Fluency Voice Technology is the leading provider of speech recognition applications for use in call centres. Our solutions enable large enterprises to significantly reduce costs and enhance customer service. Read More Company Technical Support News and Events ... Industry Solutions Fluency works with leading organisations across a number of verticals helping them to achieve key business challenges. Managed Services Not ready to invest? Host your speech application on a Fluency platform Web Seminar Speech Survey Discover what consumers really think about speech PDF (186KB) Case Study: Barclays Exclusively Ours (pdf) Read about our work with Barclays Successful Calls (pdf) The Importance of Voice User Interface Design Fluency Appoints Industry Professional David Johnson To Head Professional Services Team
Extractions: Talk ... Newswatch Last Updated: Tuesday, 21 December, 2004, 09:25 GMT E-mail this to a friend Printable version Speech takes on search engines The search engine can read out results in three voices A Scottish firm is looking to attract web surfers with a search engine that reads out results. Called Speegle, it has the look and feel of a normal search engine, with the added feature of being able to read out the results. Scottish speech technology firm CEC Systems launched the site in November. But experts have questioned whether talking search engines are of any real benefit to people with visual impairments. 'A bit robotic' The Edinburgh-based firm CEC has married speech technology with ever-popular internet search. The ability to search is becoming increasingly crucial to surfers baffled by the huge amount of information available on the web. Blind people have specialised screen readers available to them which will do the job these technologies do in a more sophisticated way
Speech Analysis A detailed paper describing some of the technology of speech recognition. http://mi.eng.cam.ac.uk/~ajr/SA95/
Éíóôéôïýôï Åðåîåñãáóßáò ôïõ Ëüãïõ - Institute For Founded in Athens, under the auspices of the General Secretariat for Research and technology (Ministry of Development) with the aim to support the development of Language technology. http://www.ilsp.gr/
Extractions: university A-Z sotONLINE home About ECS ... Contact ISIS Featured Project This project investigates the problem of classifying and predicting fatigue crack initiation sites, through microstructure quantification in Austempered Ductile Iron. The aim of this work is to build... [ more Research Areas Image Processing and Computer Vision Speech Science and Technology Intelligent Systems and Machine Learning Systems and Control Welcome to the Image, Speech and Intelligent Systems (ISIS) Research Group , which is part of the School of Electronics and Computer Science at the University of Southampton
Printacall Manufactures communications technology for deaf, hearing impaired and speech impaired people. http://www.printacall.com.au
Extractions: Australia's leading organisation for products for hearing impaired, speech impaired and Deaf people. Assistive devices to enable a person with a hearing disability to communicate with others by telephone, or hear sound with greater clarity depending on the individual hearing loss. Printacall, with 20 years of expertise in audio induction loop systems for public buildings and the supply and maintenance of text telephones(TTYs), supply and install Sound field amplification systems. Printacall specialise in Sound Field systems, or enhanced learning systems as they are sometimes referred to. Soundfield is a method of amplifying a teacher's voice to overcome the effects of distance, noise and reverberation. Soundfield systems provide a quality listening environment for every student and are perfect for classrooms, meeting rooms and lecture halls. Contact our friendly staff for more information. We can assist you in identifying what is best for your needs and may be able to assist you in your presentation of information to stakeholders.
NIST Speaker Recognition - Eval 2001 The 2001 NIST Speaker Recognition evaluation is part of an ongoing series of yearly evaluations conducted by NIST. These evaluations provide an important contribution to the direction of research efforts and the calibration of technical capabilities. They are intended to be of interest to all researchers working on the general problem of text independent speaker recognition. To this end the evaluation was designed to be simple, to focus on core technology issues, to be fully supported, and to be accessible. http://www.nist.gov/speech/tests/spk/2001/index.htm
Extractions: The 2001 NIST Speaker Recognition Evaluation The 2001 NIST Speaker Recognition evaluation is part of an ongoing series of yearly evaluations conducted by NIST. These evaluations provide an important contribution to the direction of research efforts and the calibration of technical capabilities. They are intended to be of interest to all researchers working on the general problem of text independent speaker recognition. To this end the evaluation was designed to be simple, to focus on core technology issues, to be fully supported, and to be accessible. Posted: 02/11/03 Evaluation Answer Keys for the 2001 NIST Speaker Recognition Evaluation Updated: 02/26/2001 Resources for the extended data task are now available. NIST Speaker Recognition web-site comments and corrections should be E-mailed to Mark Przybocki Created: 04-Oct-2000 Last updated: 11-Feb-2004
Trout's Internet Clock Analog desktop clock, scheduler, time synchronizer, and world clocks for different time zones. Uses Microsoft Agent technology for textto-speech announcements. http://www.chemware.co.nz/tic.htm
Extractions: with a Message, Song, Multimedia Presentation or a Microsoft Agent character Set applications to run later Make sure your computer has the right time - Synchronize with Internet Atomic Clocks and Time Servers or set it offline See what time it is somewhere else in the World - up to extra individual 10 Time Zone Clocks Liven up your desktop with an Analog Clock face using any picture you like Add an analog clock to your system tray Top Key Features . . . have a look at some screen shots Tweaking the Clock - Any Shape , Size, Color, Effects... Dynamic Icons - When you run Trout's Internet Clock, all its icons are functional clocks. Including, of course, the one on the system tray.
Adducive Silicon Valley based voice user interface design consulting, with expertise in overthe-phone speech recognition applications using technology from Nuance and speechWorks. http://www.adducive.com
Extractions: Welcome! I am no longer actively seeking consulting work, but my website will continue to explain the services that a user interface designer can provide and to serve as a place for my portfolio and articles. Even though I am no longer seeking consulting work, this collection of resources might be useful to other designers and people who are hiring designers. You can find information on speech recognition and IVR application design , and a collection of links to useful user interface design articles To keep up with what I'm doing now, you might be interested in the Brian2Brian blog I write with another interesting Brian I am not hiring, but I am happy to answer questions from young people interested in the field who have run across my website. My e-mail address is brk@adducive.com These are the pages most likely to be new to you since your last visit. Ten websites I like for rational and irrational reasons. A two minute video covering the history and future of user interfaces gets me thinking that the future may be no better than the past unless technologists learn that it's their attitudes toward people and not their adoption of technology that matters.
LTG Software: LT TTT Text tokenization system and toolset, including transducer and separate partof-speech tagger. License information, sample output, documentation. From the Edinburgh Language technology Group. http://www.ltg.ed.ac.uk/software/ttt/
Extractions: LT TTT is a text tokenization system and toolset which enables users to produce a swift and individually-tailored tokenisation of text. Although LT TTT is separate from our other XML tools, it is part of the same philosophy of modular tools with stream input/output which are combined together in a pipeline. The LT TTT tools use the XML-handling API provided with the LT XML library. The release now available runs on Solaris 2.5. The main component of the LT TTT system is a program called fsgmatch . This is a general purpose cascaded transducer which processes an input stream deterministically and rewrites it according to a set of rules provided in a grammar file. It can be used to alter the input in a variety of ways, although the grammars provided with the LT TTT system are all used simply to add mark-up information. With LT TTT come grammars to segment texts into paragraphs, segment paragraphs into words, recognise numerical expressions, mark-up money, date and time expressions in newspaper texts, and mark-up bibliographical information in academic texts. These grammars are accompanied by detailed documentation which allows you to alter grammars to suit your own needs or develop new rule sets for particular purposes. While the bulk of tokenisation is performed using hand-crafted rules, the LT TTT system also contains components where the rules result from machine learning. There are two of these statistical components: the first is a part-of-speech tagger which assigns syntactic category labels to words; the second is a sentence boundary disambiguator which determines whether a full-stop is part of an abbreviation or a marker of a sentence boundary. These components are also distributed separately as
Welcome To Artificial Intelligence Group Research, personnel, publications and events of The speech and Language technology group, part of the University of Patras, specialising in speech processing, natural language processing and optical character recognition. http://slt.wcl.ee.upatras.gr
The Sydney Morning Herald The text of Rupert Murdoch s speech to the to the American Society of NewspaperEditors. The Sydney Morning Herald. http://www.smh.com.au/news/Technology/Text-of-Murdochs-speech/2005/04/14/1113251
Extractions: @import url("http://smh.com.au/css/smh.css"); @import url("http://fdimages.fairfax.com.au/cui/netstrip-20050427.css"); NEWS MYCAREER DOMAIN DRIVE ... register Login below if you have a Fairfax Digital username, or have registered for The Sydney Morning Herald, The Age, RugbyHeaven, or Realfooty. Username: Password: Forgotten your password? Note! You do not need to login every time you visit, provided your browser accepts cookies. More About registration: You are now required to register for full access to The Sydney Morning Herald. Please fill out the short form below to register. Contact us if you are blind or vision impaired. Indicates required information Step 1: Create your account Create a Username: Minimum 4 characters. No spaces allowed. You can use your email address. Create a Password: Minimum 4 characters. No spaces allowed. Case sensitive (a is different from A) Confirm Password: Email Address: You will not be spammed as a result of registering with us. More Email Format: HTML (with graphics) Plain Text
SoundLinks Home Page Specialists in audio and speech access offering training and consultancy in how to work effectively with a range of adaptive and mainstream technology. http://www.soundlinks.com/
Extractions: Linking People with Information We can provide training and consultancy in how to work effectively and productively, with a range of adaptive and mainstream technology, in the following areas: Efficient and relevant use of the Internet audio production music technology Accessibility and usability in design of new products Training , consultancy, installation and support are offered for a range of Speech-based Internet Access software including the Sonar music sequencer and multitrack audio package. SoundLinks can also provide consultancy and presentations explaining how this technology can be especially useful for people who have difficulty reading print, as well as good practice in designing accessible Web sites. SoundLinks also maintains close links with BCAB,
Extractions: Easter Seals South Carolina has experienced a taste of the wonderful benefits offered from the national relationship between Century 21 and Easter Seals. We are excited about the growing relationship with Century 21 and are grateful for the efforts being made to increase awareness and support of the services we are providing to children and adults with disabilities across our state. For more information about Easter Seals South Carolina and our Century 21 relationshp, please
TIFR - Speech Signal Processing Recognition and synthesis of spoken Indian languages at Tata Institute of Fundamental Research. speech workshop scheduled for Jan 2003. http://speech.tifr.res.in