Speech

Nuance Communications has updated its leading speech-to-text application Dragon Dictate for Mac to version 3, and Gizmag goes hands-on to investigate whether it can finally offer software-based dictation which is both practical and appealing, when compared to manual typing.  Read More

Researchers at the Norwegian University of Science and Technology (NTNU) are combining two of the best-known approaches to automatic speech recognition to build a better and language-independent speech-to-text algorithm that can recognize the language being spoken in under a minute, transcribe languages on the brink of extinction, and make the dream of ever present voice-controlled electronics just a little bit closer.  Read More

Recently, scientists unlocked the code used by neurons in the retina for sending visual data to the brain. This allowed them to create a device that restored almost-normal vision to blind mice. Now, another group of scientists has announced that they have determined the brain’s code for pronouncing vowels, and they believe that their discovery could lead to machines that speak for people who are physically unable to do so.  Read More

Since beginning in 2003, the Microsoft Imagine Cup has tasked students the world over with developing technology aimed at solving real-world problems. In this, its 10th year, students were asked to build their project around a specific Millennium Development Goal (MDG), with the finals held this month in Sydney, Australia. The winners have just been announced and beating out teams from 75 countries to claim first place (and US$25,000) in the Software Design category was the Ukraine’s quadSquad with their EnableTalk gloves that translate sign language into speech in real time.  Read More

iCub is an open-source hardware project described as a “cognitive humanoid robotic platform." The project was initiated in Italy, but the technology is now in use at several other labs, including the University of Hertfordshire. Researchers there, taking part in the iTalk project, have carried out experiments to find out how robots can develop basic language skills by interacting with a human.  Read More

For some time now, speech-recognition programs have existed that attempt to reproduce the user’s spoken words in another language. Such “speech-to-speech” apps, however, provide their translations using a very flat, synthetic voice. Now, experimental new software developed by Microsoft is able not only to translate between 26 different languages, but it plays the translated speech back in the user’s own voice – complete with the inflections they used when speaking in their own language. It looks like a real-life version of Star Trek’s universal translator could soon be here.  Read More

For those who don't suffer the talkative gladly, a pair of Japanese researchers may have come up with just the thing - a portable device that can painlessly jam a person's speech from up to 30 meters (98 ft) away. Ingeniously dubbed the "SpeechJammer," you aim it like a gun and, if it's anywhere near as effective as the Delayed Auditory Feedback exhibit I tried at my local science museum, it works like a charm.  Read More

Whether it’s people who can’t speak, or musicians looking for a new way of expressing themselves, both may end up benefiting from an experimental new gesture-to-voice synthesizer. The system was created at the University of British Columbia, by a team led by professor of electrical and computer engineering Sidney Fels. Users just put on a pair of sensor-equipped gloves, then move their hands in the air – based on those hand movements, the synthesizer is able to create audible speech.  Read More

You may think that Stephen Hawking’s synthesized voice sounds a little ... unusual, but imagine how much weirder it would be to witness a child using that same adult voice to communicate. For many children who are unable to speak, however, they have no choice but to use assistive devices that utilize just such a voice. Now, help may be on the way. Norwegian researchers have developed a new method of creating synthetic speech, that actually sounds like it is being spoken by a child. Such technology could also allow computers to better recognize words spoken to them by young users.  Read More