Building Speech Applications Just Got Easier: AT&T Releases Speech API
false Speech interfaces are becoming de rigueur because users find them easy to use. But implementing these interfaces is not easy. Speech technologies are complex and require expert kno
StorEBook: How Goldilocks and the Three Bears is Driving Text-to-Speech Technology
true When it comes to critics of machine-generated speech, three-year-olds might be the toughest ... and a wolf better huff and puff. Current text-to-speech (TTS) systems are not up to
iPizza Speech Mashup
false Speech mashup Speech mashups provide an easy way for web developers to incorporate a speech ... . All speech and language processing, from automatic speech rec
Spectra - Speech-to-speech translation
machine translation, ASR, TTS, recognition Spectra - Speech-to-speech translation EA11024_Spectra_NEW.mp4 false false This video is a demonstration of the Spectra speech-to-
At AT&T Labs - Research, we apply our speech, language and media technologies to give people with disabilities more independence, privacy and autonomy.
AT&T Research is developing a real-time speech-to-speech translation technology so the translation starts as soon as speech is detected.
On the Intelligibility of Fast Synthesized Speech for Individuals with Early-Onset Blindness
On the Intelligibility of Fast Synthesized Speech for Individuals with Early-Onset Blindness ABSTRACT People with visual disabilities increasingly use text-to-speech synthesis as a pri
Role of Pausing in Text-to-Speech Synthesis for Simultaneous Interpretation
Role of Pausing in Text-to-Speech Synthesis for Simultaneous Interpretation Vivek Kumar ... , Florham Park, NJ 07932, USA Abstract The goal of simultaneous speech-to-speech (S2
iPizza Speech Mashup
This video demonstrates the use of AT&T's Speech Mash service to implement a smartphone web application that permits a customer to order a pizza completely by voice.
Reducing time for annotating speech data to develop a dialog application
Systems and methods for annotating speech data. The present invention reduces the time required to annotate speech data by selecting utterances for annotation that will be of greatest be