In the last decade, the speech technology market has evolved radically, owing to mergers and acquisitions that have led to a consolidation of the sector and resulted in just a few dominant players.
Loquendo (News - Alert), created in 2001 from the technological core of Telecom Italia, put out a white paper explaining the basics of speech technology. Here is a basic overview of a few of the major points the paper covers:
Interacting with machines that listen, understand and react to human stimuli has been for many years the holy grail of scientists across disciplines. First attempts to build such machines dates back to Kratzenstein's and Von Kempelen's 18th century mechanical speech synthesizer. However, it was not until first programmable computers were invented that computer scientists experimented with models of language understanding and human- interaction.
Speech synthesis technology, or Text-To-Speech, developed by Loquendo, enables the real time conversion of any written message or application prompt into speech. Automatic speech recognition, or ASR, allows the user to interact with an automated system using their own voice. These technologies are available in numerous languages and are widely found in interactive telephony services, multimedia applications and embedded systems.
Voice platforms were created following the development of standards, VoiceXML (News - Alert) in particular, as systems able to download via http a voice service and interpret it, then managing TTS and ASR speech technologies. Moreover, speech technologies are accessed in a standardized way using a protocol defined by the IETF, the Media Resource Control Protocol. In this way the ASR and TTS technologies are kept separate from the rest of the platform and can be allocated and managed independently from the rest of the platform.
Loquendo Embedded Speech Technologies are innovative and easy to integrate, available on navigation systems, PNDs, smartphones and virtual assistants on the websites of leading companies all over the world.
For more, check out the Speech Recognitionchannel on TMCnet.
David Sims is a contributing editor for TMCnet. To read more of David's articles, please visit his columnist page. He also blogs for TMCnet here.
Edited by Stefania Viscusi