H.A.L. 9000 from 2001: A Space Odyssey. Lost in Space’s B-9, that sounded the warning, “Danger Will Robinson!” Number 5, the electrified robot from Short Circuit. What do these artificial life forms have in common? Movies with cheesy writing and bad graphics? No. Two words: speech synthesis.
The first computer-based speech synthesis systems came about in the 1950s. Technology quickly advanced, and by the 1970s, handheld electronics with speech synthesis emerged, like Texas Instruments’ Speak & Spell, and arcade games such as Stratovox and Berzerk.
The key elements of speech synthesis systems are the degree of naturalness and intelligibility of the speech. There are two synthetic waveforms associated with creating these characteristics – concatenative synthesis and formant synthesis. Concatenative is arguably the most natural because it strings together pre-recorded sounds; however, computerized formant speech is clearly understandable even at a rapid fire pace.
Speech synthesis is a integral part of IVR systems; those awesome automated answering systems call centers use to triage calls and promote self service. In a personal capacity, if you’ve ever used Siri, consider yourself experienced. Want to know more? Dig deeper into our speech synthesis paper here!
Copy the code below to use this infographic:
<img title=”Speech Synthesis Technology Infographic” alt=”Speech Synthesis Technology Infographic” src=”http://www.specialtyansweringservice.net/wp-content/uploads/infographic-explaining-speech-synthesis-technology/speech-synthesis-infographic.jpg” width=”710″ />
<pre><em>Image originally posted on <a href=”http://www.specialtyansweringservice.net/infographic-explaining-speech-synthesis-technology/”>The SAS Blog</a></em>