haskins logo
Electronic Speech Synthesis

Mechanical talking devices were rapidly replaced by electronic speech simulators (known as speech synthesizers), as technological developments made experimentation more affordable. Models of the human vocal tract could now be created in the form of electrical circuits, leading to the creation of dedicated hardware speech synthesizers. 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). The advent of desktop computing in the 1980s and 1990s brought affordable speech synthesis and recognition within the reach of the average computer user.

Some general sites related to speech synthesis include:

    comp.speech FAQ (Frequently Asked Questions)

    John Iles' overview of Speech Synthesis Systems (NF)

    SpeechLinks Speech Synthesis HyperLinks (NF)

    Speech on the Web

    Speech Synthesis overview (Mark Tatham) (NF)

Acoustic Speech Synthesis
Digital computers can be used to control the acoustic parameters/characteristics of the speech signal. By carefully creating the relevant acoustic information, speech tokens (phonemes, syllables, words, sentences, etc.), can be generated. A variety of different techniques are used, and a number of different aspects of the acoustic information can be manipulated, including the waveform, the formants (the main bands of acoustic energy that correspond to the resonances of the vocal tract), Linear Predictive Coding (LPC) parameters, etc. Below are listed some additional sites related to the synthesis of speech. Many more can be found on the web.

    AT&T Research Voices (NF)

    Expressive Synthesized Speech

    Haskins Laboratories Sinewave Synthesis

    ICP (Grenoble) Speech Synthesis (NF)

    KTH: synthetic speech with emotions examples (NF)

    National Center for Voice and Speech: Pavarobotti (NF)

    Sensimetrics SenSyn (formant based commercial synthesizer)

    Examples of Synthesized Speech (Gregor Möhler)

    Speech Synthesis Demonstrations (Klatt 1987) (NF)

Text-to-Speech (TTS) Synthesis
In these models, speech sounds are generated by rule from text that is input to the synthesizer. Examples of and information about Text-to-Speech (TTS) synthesis can be found at a number of sites, including:


    AT&T Advanced Speech Products Group

    Bell Labs Text-to-Speech Synthesis

    entropic truetalk (commercial TTS)


    The Festival Speech Synthesis System (CSTR, Edinburgh)

    ICP Museum of Speech Synthesis (TTS examples)

    Microsoft Whistler TTS Synthesis

    ProSYNTH (U. of Cambridge)

    SAY ... (interactive rsynth TTS)

    Speech Technology Group (Spanish TTS)

    SVOX (German TTS)