Chapter 16: Language and Computers

0.0(0)
studied byStudied by 2 people
learnLearn
examPractice Test
spaced repetitionSpaced Repetition
heart puzzleMatch
flashcardsFlashcards
Card Sorting

1/23

Study Analytics
Name
Mastery
Learn
Test
Matching
Spaced

No study sessions yet.

24 Terms

1
New cards
Intelligibility
how well listeners can recognize and understand the individual sounds or words generated by the synthesis system.
2
New cards
Pronunciation modeling
used to filter out unlikely sound sequences.
3
New cards
Domain
specific synthesis- create utterances from prerecorded words and phrases that closely match the words and phrases that will be synthesized.
4
New cards
Noisy channel model
treats speech input as if it has been passed through a communication channel that garbles the speech waveform.
5
New cards
Filter
shapes the sound created by the source into the different sounds we recognize as speech sounds.
6
New cards
Naturalness
how much the synthesized speech sounds like the speech of an actual person.
7
New cards
Isolated speech
the user speaks the input clearly and without extraneous words.
8
New cards
Acoustic modeling
mapping the energy values extracted during signal processing.
9
New cards
Concatenative Synthesis
uses recorded speech by stringing together pieces of the recorded speech and then smoothing the boundaries between them.
10
New cards
Source filter theory
there are two independent parts to the production of speech sounds.
11
New cards
Monitor corpus
as new texts continue to be written or spoken, more data is gathered.
12
New cards
Reference corpus
specified amount of text that has been collected and annotated.
13
New cards
Corpora
can be classified by the genre of the source material.
14
New cards
Word spotting
a program focuses on words it knows and ignores ones it doesnt.
15
New cards
Signal processing
recording the speech waveform with a microphone and storing it in a manner that is suitable for further processing by a computer.
16
New cards
Partial Automation
the source language text can first be pre- edited by a person so as to "prime "it for a machine translation system.
17
New cards
Language modeling
calculating the probability of sequences.
18
New cards
Synthesized speech
piecing together smaller recorded units of speech into new utterances.
19
New cards
Speech synthesis
the use of a machine, usually a computer, to produce human- like speech.
20
New cards
Corpus
can be composed from spoken, signed or written language.
21
New cards
Signal processing
recording the speech waveform with a microphone and storing it in a manner that is suitable for further processing by a computer
22
New cards
Acoustic modeling
mapping the energy values extracted during signal processing
23
New cards
Pronunciation modeling
used to filter out unlikely sound sequences
24
New cards
Language modeling
calculating the probability of sequences