Difference between revisions of "Speech synthesis"
Wohlgemuth (talk | contribs) m (from utrecht) |
(Added the "see also" section) |
||
| Line 1: | Line 1: | ||
| + | ==Definition== | ||
Speech can be generated artificially in several ways. Fragments of natural speech can be used as building blocks as in diphone synthesis and [[concatenation]]. The speech can also be entirely artificial whereby the acoustic properties of the vocal tract are imitated, e.g. the [[vocoder]], Klatt formant synthesis, [[articulatory speech synthesis]], and the [[Pattern Playback]] synthesiser. Electronic speech synthesis emerged, as technological developments made experimentation more affordable. Models of the human vocal tract could now be created in the form of electrical circuits. A revolution occurred in speech technology when the digital computer permitted the simulation of electronic circuitry, the conversion of analog signals to digital form, and the creation of analog signals from digital information (in this case, sound in the form of speech). | Speech can be generated artificially in several ways. Fragments of natural speech can be used as building blocks as in diphone synthesis and [[concatenation]]. The speech can also be entirely artificial whereby the acoustic properties of the vocal tract are imitated, e.g. the [[vocoder]], Klatt formant synthesis, [[articulatory speech synthesis]], and the [[Pattern Playback]] synthesiser. Electronic speech synthesis emerged, as technological developments made experimentation more affordable. Models of the human vocal tract could now be created in the form of electrical circuits. A revolution occurred in speech technology when the digital computer permitted the simulation of electronic circuitry, the conversion of analog signals to digital form, and the creation of analog signals from digital information (in this case, sound in the form of speech). | ||
| − | == | + | ==See also== |
| + | *[[Talking machines]] | ||
| + | *[[Analysis-by-synthesis]] | ||
| + | == Links == | ||
* [http://www2.let.uu.nl/UiL-OTS/Lexicon/zoek.pl?lemma=Speech+synthesis&lemmacode=1305 Utrecht Lexicon of Linguistics] | * [http://www2.let.uu.nl/UiL-OTS/Lexicon/zoek.pl?lemma=Speech+synthesis&lemmacode=1305 Utrecht Lexicon of Linguistics] | ||
* [http://tcts.fpms.ac.be/synthesis/mbrola.html Tutorial on speech synthesis] | * [http://tcts.fpms.ac.be/synthesis/mbrola.html Tutorial on speech synthesis] | ||
Latest revision as of 07:08, 17 August 2014
Definition
Speech can be generated artificially in several ways. Fragments of natural speech can be used as building blocks as in diphone synthesis and concatenation. The speech can also be entirely artificial whereby the acoustic properties of the vocal tract are imitated, e.g. the vocoder, Klatt formant synthesis, articulatory speech synthesis, and the Pattern Playback synthesiser. Electronic speech synthesis emerged, as technological developments made experimentation more affordable. Models of the human vocal tract could now be created in the form of electrical circuits. A revolution occurred in speech technology when the digital computer permitted the simulation of electronic circuitry, the conversion of analog signals to digital form, and the creation of analog signals from digital information (in this case, sound in the form of speech).
