CS4705

1
Lecture 4

• CS4705
• Sound Systems and Text-to-Speech

2
Sound Systems of Language

• Phonetics
• The sounds (phones) of the worlds languages, the
  phonemes they map to, and how they are produced
• Phonology
• Rules that govern how phones are realized
  differently in different contexts
• Technologies
• Automatic Speech Recognition (ASR) systems take
  sounds as input and output word hypotheses
• Text-to-Speech (TTS) systems take text as input
  and produce speech

3
Letters and Sounds

• same spelling different sounds
• o comb, tomb, bomb oo blood, food, good
• c court, center, cheese s reason, surreal,
  shy
• same sound different spellings
• i sea, see, scene, receive, thief s
  cereal, same, miss
• u true, few, choose, lieu, do ay prime, buy,
  rhyme, lie
• combination of letters single sound
• ch child, beach th that, bathe
• oo good, foot gh laugh
• single letter combination of sounds
• x exit, Texas u use, music
• silent letters
• k knife, know p psycho, pterodactyl
• e moose, bone gh through

4
Articulators
palate
larynx
trachea
5
Articulators in action
(Sample from the Queens University / ATR Labs
X-ray Film Database)
Why did Ken set the soggy net on top of his
deck?
6
Vocal fold vibration
UCLA Phonetics Lab demo
7
Places of articulation
http//www.chass.utoronto.ca/danhall/phonetics/sa
mmy.html
8
Articulatory parameters for English consonants
(in ARPAbet)
MANNER OF ARTICULATION
VOICING
9
American English vowel space
10
Acoustic landmarks
Patricia and Patsy and Sally
11
Syllables

• Syllabification important for
• pronunciation deny/denim
• speaking rate calculation syllables per second
• word recognition in ASR
• (onset) nucleus (coda)
• c a t
• a
• a t
• t o
• Lexical stress primary, secondary, terciary
• telephone

12
Phonological Rules

• Not all instances of a given phone x sound/look
  alike
• Phoneme /x/ may have many allophones
• Phonological rules map phonemes in context to
  allophones, e.g.
• simple rules /t,d/ --gt ?/ V _ V
• FSAs, FSTs
• declarative constraints t ? ? V _ V

13
Allophones of /t/

• What we would consider a single sound can be
  pronounced differently depending on the phonetic
  context. For example, the phoneme /t/

Figure 4.8 Jurafsky Martin (2000), page 104.
14
Application Word Pronunciation for TTS

• Pronouncing dictionaries (the dhax,dhiy)
• Problems
• Homographs (bass/bass, wind/wind, desert/desert)
• Abbreviation (dr., st.)
• Numbers (2125551212)
• Acronyms (NAACL, IDIAP)
• Morphological variation (unrelentingly)
• Proper names and unknown words
• rules dictionaries/dictionaries rules

15

• Hybrid model
• FSTs model individual word pronunciation in
  lexicon (e.g. reg-noun-stem entry ck aae tt)
• FSAs model morphology (e.g. reg-noun-stem s)
• FSTs for pronunciation rules (e.g. s--gt z)
• special rules to model name and acronym
  pronunciation
• default letter2sound rules for other words

16
Inventive (and sometimes useful) Approaches for
Pronouncing Unknown Words

• Rhyming analogy varoom/room, todo/dodo
• Linguistic origin Infiniti, vingt, Perez
• Abbreviation expansion
• spacious living/dining rm w/frplc/dining room
  with fireplace
• pls?

17
Summary

• Phones realize phonemes in different contexts
• Different places and manners of articulation
  result in acoustic differences that can be
  detected by ASR systems as well as people
• Versatile FSTs can model phonological as well as
  morphological and spelling systems
• Many creative approaches toward pronunciation
  modeling for TTS
• Next time Read Ch 6 (Guest Speaker Sameer
  Maskey)