Tweetrad.io: Listen to Twitter Search Results

Here’s something fun and amusing. We just happened upon Tweetrad.io, a site that treats tweets from your Twitter searches like tunes on an old school radio channel, so tweets are read aloud by an automated Twitter DJ as they roll in.

The site is self-explanatory, as you can search for tweets, or select from the pre-programmed channels or trending topics, and listen to the tweets instead of having to waste the effort of actually reading them. It may sound a little a dry in theory, but in practice, it’s absolutely hilarious.

Report: iPhone 3.0 may include voice recognition, synthesis features

rumors suggest that the iPhone may soon be more receptive to my pleas: Ars Technica reports thatuncovered software frameworks in the iPhone 3.0 beta might represent speech recognition and synthesis systems.

Of course, this isn’t exactly out of left field. Both the latest iPod nano and iPod shuffle include speech synthesis capabilities, dubbed Spoken Menus in the 4G nano and VoiceOver in the iPod shuffle, that allow users to navigate the devices without having to look at the screen. In both cases it helps people who are visually impaired use the devices, but in the shuffle it’s also a necessity, since the device has no screen and a potentially confusing control scheme.

The iPhone and iPod touch are extremely difficult for visually impaired users to interact with, as they have little in the way of tactile cues or feedback. Voice recognition in particular has been a heavily requested feature, as it could improve not just accessibility, but everyday tasks such as dialing a number without having to look at the phone’s screen—handy for when you’re driving, for example.

The power of (synthetic) speech

A single spoken word takes three breaths and a great deal of willpower for Geoffrey Roberts: like thousands of people, he has cerebral palsy, which also makes his speech nearly unintelligible to those who do not know him. His limited speech is a source of great frustration for his otherwise nimble mind.

That is why a technology being developed at Barnsley Hospital and Sheffield University is nothing short of revolutionary for people like him. The Voice Input Voice Output Communication Aid (Vivoca) uses speech recognition technology to translate severely distorted words into clear sentences. It can also communicate entire sentences having heard only one or two key words.

The aid consists of a handheld computer and a wireless Bluetooth headset. Users will also be able to choose from a range of male and female recorded voices and regional dialects. Voices in the bank already include the Barnsley poet Ian McMillan and the Yorkshire BBC newsreader Christa Ackroyd. People who are slowly losing their speech - through Parkinson's or motor neurone disease, for instance - can record their voice before it has completely deteriorated.

Eric – New Hollywood Star

IVO Software has presented Eric – the latest English-speaking male voice based on IVONA – text-to-speech technology regarded as one of the best in the world.  Eric comes from Hollywood and experts describe his way of speaking as “CNN style”.  Listening to Eric you get the impression that this is a person from the West Coast of the US talking to you. This is no accident as IVONA is speaking with the voice of an artist heard in Hollywood blockbusters and on CNN. To find out what Eric can say visit www.ivona.com. Just select his voice and then enter any text in the appropriate box for Eric to read it out. The service allows you to send your friends interesting pieces of information read out by Eric or to post them on a blog. 

[click heading for more]

Voxpilot Partners With Cepstral to Offer Affordable Quality Text-to-Speech Voices

Cepstral LLC today proudly announced a partnership with Voxpilot, a leader in VoiceXML and interactive voice and video platforms. Cepstral's Text-to-Speech (TTS) engine and voices have undergone interoperability testing and Voxpilot will offer in-house support for Cepstral's server-grade TTS engine and voices.
Voxpilot integrated Cepstral's engine into the version 3.4 release of their premiere product, Voxpilot Open Media Platform. Customers of the Voxpilot Open Media Platform can now reach enterprise-level scale for their speech needs including spoken alerts, auto-attendant, and notifications more affordably using Cepstral's high quality TTS voices. [click heading for more]

George Bush's voice speech synthesised for Text-to-speech

Ok folks, this is just for fun, but on my web travels I discovered this speech synthesis of George Bush using the Cereproc TTS engine. Quality is what you would expect from a voice built from a mixed-bag of public domain speech samples, but actually, it's rather convincing.

For a long time we've never been able to believe photographs thanks to the awesome power of Adobe Photoshop. Perhaps the time when the same is true of voice recordings is soon upon us... [click heading for more]

Customers in Romania? Have Them Speak to 'Carmen'

There is now help available for Romanian-serving contact centres. ‘Her’ name is Carmen. ‘She’ is the first high quality synthetic Romanian-language voice and ‘works’ in IVONA Telecom TTS speech recognition application, developed and marketed by IVO Software, which is based in Poland. Carmen joins her ‘friends’, Jacek and Ewa who can talk to Polish-speaking callers, and who were the first members of the IVONA Telecom TTS ‘family’, along with Jennifer, who can converse with Americans . [click heading for more]

Welsh language-technology gets global recognition

TECHNOLOGY aimed at helping businesses use the Welsh language has been so successful it is being copied as far afield as China and Sri Lanka.
A small team at Canolfan Bedwyr, a unit at Bangor University, has for several years been creating Welsh-language computer spell-checkers, screen readers and synthetic voices.

The unit – which brings together linguists and IT experts – also creates generic computer tools that can be adapted for use in other languages.
The centre’s model for standardising technical terms was borrowed recently by the Chinese government when it introduced new legislation. [click heading for more]

Telisma looks to Collaborate with Indian Firms [CxO today]

Telisma, a France-based company that develops speech recognition software, looks forward to collaborating with Indian firms having expertise in Text to Speech (TTS) and Text to Text (TTT) technology. The company is scouting to collaborate with Indian companies, academic institutions that can deliver capabilities - such as TTS, TTT, and translation to its existing capability of speech recognition.

The company depends highly on its partners such as Wipro, Genesys in India, Cisco, Cap Gemini, Atos Origin, and others globally, as this is the only mode through which it sells its software.

Cepstral Donates Open Source MRCP Stack to Telephony Industry

Cepstral LLC announced that it is providing the first open source Media Resource Control Protocol (MRCP) library, OpenMRCP, at no charge to telephony application developers. Cepstral, a pioneer in Text-to-Speech (TTS) voice software, is donating OpenMRCP to the developer community in order to spur the development of telephony applications that interact with distributed speech resources such as TTS and Automatic Speech Recognition (ASR). MRCP is a standards-based communications protocol that allows telephony applications to communicate with speech resources, similar to the way TCP/IP allows browsers to communicate with web sites. [click heading for more]