Chapter 16: Language and Computers

Intelligibility

how well listeners can recognize and understand the individual sounds or words generated by the synthesis system.

Pronunciation modeling

used to filter out unlikely sound sequences.

Domain

specific synthesis- create utterances from prerecorded words and phrases that closely match the words and phrases that will be synthesized.

Noisy channel model

treats speech input as if it has been passed through a communication channel that garbles the speech waveform.

Filter

shapes the sound created by the source into the different sounds we recognize as speech sounds.

Naturalness

how much the synthesized speech sounds like the speech of an actual person.

Isolated speech

the user speaks the input clearly and without extraneous words.

Acoustic modeling

mapping the energy values extracted during signal processing.

Concatenative Synthesis

uses recorded speech by stringing together pieces of the recorded speech and then smoothing the boundaries between them.

Source filter theory

there are two independent parts to the production of speech sounds.

Monitor corpus

as new texts continue to be written or spoken, more data is gathered.

Reference corpus

specified amount of text that has been collected and annotated.

Corpora

can be classified by the genre of the source material.

Word spotting

a program focuses on words it knows and ignores ones it doesnt.

Signal processing

recording the speech waveform with a microphone and storing it in a manner that is suitable for further processing by a computer.

Partial Automation

the source language text can first be pre- edited by a person so as to "prime "it for a machine translation system.

Language modeling

calculating the probability of sequences.

Synthesized speech

piecing together smaller recorded units of speech into new utterances.

Speech synthesis

the use of a machine, usually a computer, to produce human- like speech.

Corpus

can be composed from spoken, signed or written language.

Signal processing

recording the speech waveform with a microphone and storing it in a manner that is suitable for further processing by a computer

Acoustic modeling

mapping the energy values extracted during signal processing

Pronunciation modeling

used to filter out unlikely sound sequences

Language modeling

calculating the probability of sequences