Phonetics and Speech Feature Extraction

15.3 Prosody

1. Define prosody.
   The study of intonational and rhythmic aspects of language, especially the use of F0, energy and duration to convey pragmatic, affective, or conversation-interactional meaning.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
2. What perceptual qualities correspond to energy and F0?
   Energy → loudness. F0 → pitch.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
3. What are the main functions of prosody?
   Marking discourse structure (e.g. statements vs questions), marking saliency of words/phrases, paralinguistic functions (emotion like happiness, surprise, anger), and managing conversational turn-taking.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
4. What does prosody mean in poetry?
   The study of verse metrical structure.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
5. What is prominence, and how do English speakers make a word more prominent?
   Perceptual salience to the listener. Made by saying it louder, slower (longer duration), or with higher/more variable F0.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
6. What is a pitch accent?
   A linguistic marker representing prominence; prominent words/syllables are said to bear a pitch accent.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
7. What is lexical stress?
   A dictionary property of a word: the syllable that will be louder or longer if the word is accented. Pitch accent must be realized on the lexically stressed syllable (e.g. surPRISED, not SURprised).
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
8. How does the CMU dictionary mark stress? Examples?
   Vowels marked 0 (unstressed) or 1 (stressed): counter [K AW1 N T ER0], table [T EY1 B AH0 L].
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
9. How does lexical stress distinguish content (noun) from content (adjective)?
   Noun: [K AA1 N T EH0 N T] (first syllable stressed). Adjective: [K AA0 N T EH1 N T] (second syllable stressed).
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
10. What are reduced vowels and what is schwa?
    Unstressed vowels weakened further, with an incomplete articulatory gesture. Schwa [ax] is the most common, e.g. 2nd vowel of parakeet [p ae r ax k iy t].
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
11. Are all unstressed vowels reduced? Example?
    No. Any vowel (diphthongs especially) can keep full quality unstressed, e.g. [iy] stressed in eat, unstressed in carry [k ae r iy].
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
12. What levels are commonly used to represent the continuum of prominence?
    Accented, stressed, full vowel, reduced vowel.
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
13. What is prosodic phrasing?
    The idea that an utterance has a prosodic phrase structure (words group together, with breaks/disjunctures), analogous to syntactic phrase structure.
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
14. Define intonation phrase and intermediate phrase using I wanted to go to London, but could only get tickets for France.
    Two main intonation phrases, split at the comma. Within the first, lesser boundaries give intermediate phrases: I wanted | to go | to London.
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
15. How are intonation phrases related to syntax?
    They are often correlated with syntactic constituents.
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
16. How are prosodic boundaries predicted automatically (e.g. for TTS)?
    Sequence models taking raw text or text annotated with features (e.g. parse trees) make a break/no-break decision at each word boundary; trained on data like the Boston University Radio News Corpus.
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
17. What is the tune of an utterance?
    The rise and fall of its F0 over time.
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
18. Question rise vs final fall?
    Question rise: final F0 rise indicating a yes-no question. Final fall: final F0 drop indicating a declarative.
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
19. What is a continuation rise?
    A short F0 rise after each noun in a comma-separated list.
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
20. Besides questions and lists, what else do characteristic English tunes express?
    Contradiction and surprise.
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
21. What is ToBI?
    Tone and Break Indices: a theory/transcription system of intonation (Silverman et al., 1992). Each word may bear one of 5 pitch accents; each intonational phrase ends in one of 4 boundary tones. Versions exist for many languages.
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
22. List the 5 ToBI pitch accents.
    H* peak accent; L* low accent; L*+H scooped accent; L+H* rising peak accent; H+!H* step down.
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
23. List the 4 ToBI boundary tones and their meanings.
    L-L% final fall (declarative); L-H% continuation rise; H-H% question rise (yes-no question); H-L% final level plateau.
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3
24. What is a boundary tone in ToBI?
    The tone ending each intonational phrase, representing utterance-final aspects of tune.
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 15, §15.3