CS 4705 Lecture 4 CS4705 Sound Systems and Text-to- Speech.

Slides:



Advertisements
Similar presentations
Pushpak Bhattacharyya CSE Dept., IIT Bombay 31st March, 2011
Advertisements

Pronunciation Modeling Lecture 11 Spoken Language Processing Prof. Andrew Rosenberg.
Phonetics.
Chapter 2 phonology. The phonic medium of language Speech is more basic than writing. Reasons? Linguists studies the speech sounds.
From Sounds to Language
The sound patterns of language
From Sounds to Language
CS460/626 : Natural Language Processing/Speech, NLP and the Web (Lecture 35– Phonetics and phonology; syllabification) Pushpak Bhattacharyya CSE Dept.,
From Sounds to Language Lecture 2 Spoken Language Processing Prof. Andrew Rosenberg.
Introduction to Linguistics
From Sounds to Language CS 4706 Julia Hirschberg.
Jennifer J. Venditti Postdoctoral Research Associate
Introduction to Speech Production Lecture 1. Phonetics and Phonology Phonetics: The physical manifestation of language in sound waves. –How sounds are.
Matakuliah: G0922/Introduction to Linguistics Tahun: 2008 Session 2 Phonology.
Chapter 2 Introduction to articulatory phonetics
Chapter 3 Phonetics: Describing Sounds. Phonetics -study of speech sounds Sounds and symbols --use a system of written symbols --one sound represents.
Phonetics III: Dimensions of Articulation October 15, 2012.
Linguistics I Chapter 4 The Sounds of Language.
Phonetics & Phonology Jürgen Trouvain Areas of phonetics Speech production Speech acoustics Speech perception.
The sounds of language Phonetics Chapter 4.
English Pronunciation Practice A Practical Course for Students of English By Wang Guizhen Faculty of English Language & Culture Guangdong University of.
Phonetics and Phonology
Descriptive grammar term 1 Dorota Klimek-Jankowska.
Chapter 2 Speech Sounds Phonetics and Phonology
Sound Phonetics & Phonology. General considerations Speech sounds and sounds that convey meaning Their patterns Sound change.
The Sounds of Language. Phonology, Phonetics & Phonemics… Phonology, Phonetics & Phonemics… Producing and writing speech sounds... Producing and writing.
An Introduction to Linguistics
Phonological Theory.
1 Phonetics and Phonemics. 2 Phonetics and Phonemics : Phonetics The principle goal of Phonetics is to provide an exact description of every known speech.
CS 551/652: Structure of Spoken Language Lecture 2: Spectrogram Reading and Introductory Phonetics John-Paul Hosom Fall 2010.
CS : Speech, NLP and the Web/Topics in AI Pushpak Bhattacharyya CSE Dept., IIT Bombay Lecture-27: Phonology (quiz took place on 12/10/09; Lect 26.
CS460/626 : Natural Language Processing/Speech, NLP and the Web Lecture 28, 29: Phonetics, Phonology and Speech; introduce transliteration Pushpak Bhattacharyya.
Phonetics 2. Which English? What do we mean by a perfect English pronunciation? In one sense there are as many different kinds of English as there are.
Phonetics: Dimensions of Articulation October 13, 2010.
Daniel May Department of Electrical and Computer Engineering Mississippi State University Analysis of Correlation Dimension Across Phones.
Phonetics 2. Phonology 2.1 The phonic medium of language Sounds which are meaningful in human communication constitute the phonic medium of language.
Introduction to Linguistics Ms. Suha Jawabreh Lecture # 8.
Pronunciation Variation: TTS & Probabilistic Models CMSC Natural Language Processing April 10, 2003.
Jennifer J. Venditti Postdoctoral Research Associate
Introduction to Phonetics & Phonology
Statistical NLP Spring 2011
Introduction to Language Phonetics 1. Explore the relationship between sound and spelling Become familiar with International Phonetic Alphabet (IPA )
Phonetics Definition Speech Organs Consonants vs. Vowels
ACE TESOL Diploma Program – London Language Institute OBJECTIVES You will understand: 1. How each of the phonemes in English is articulated 2. The differences.
LIN 3201 Sounds of Human Language Sayers -- Week 1 – August 29 & 31.
Ch4 – Features Features are partly acoustic partly articulatory aspects of sounds but they are used for phonology so sometimes they are created to distinguish.
CS : Speech, NLP and the Web/Topics in AI Pushpak Bhattacharyya CSE Dept., IIT Bombay Lecture-25: Vowels cntd and a “grand” assignment.
CS : Speech, NLP and the Web/Topics in AI Pushpak Bhattacharyya CSE Dept., IIT Bombay Lecture-19: Speech: Phonetics (Using Ananthakrishnan’s presentation.
Chapter 3 Phonetics.
Welcome to all.
PHONETICS AND PHONOLOGY
ARTICULATORY PHONETICS
Linguistics: Phonetics
Statistical NLP Spring 2010
Structure of Spoken Language
Course: Linguistics Lecturer: Phoenix Xu
Introduction to Linguistics
Essentials of English Phonetics
2.2.2 Complementary distribution
How speech sounds are made
Speech Processing August 10, /10/2018.
Jennifer J. Venditti Postdoctoral Research Associate
Lecture A4 How we produce Speech.
Audio Books for Phonetics Research
Spoken Language Processing:Summing Up
Phonetics & Phonology Jürgen Trouvain.
Phonetics and Phonemics
Chapter 2 Phonology.
Phonetics and Phonemics
PHONETICS AND PHONOLOGY INTRODUCTION TO LINGUISTICS Lourna J. Baldera BSED- ENGLISH 1.
Presentation transcript:

CS 4705 Lecture 4 CS4705 Sound Systems and Text-to- Speech

Sound Systems of Language Phonetics –The sounds (phones) of the world’s 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

Letters and Sounds same spelling = different sounds o comb, tomb, bomboo blood, food, good c court, center, cheeses 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, beachth that, bathe oo good, footgh laugh single letter = combination of sounds x exit, Texasu use, music ‘silent’ letters k knife, knowp psycho, pterodactyl e moose, bonegh through

Articulators lips teeth Alveolar ridge velum uvula pharyngeal vocal folds:glottis larynx trachea palate

Articulators in action “Why did Ken set the soggy net on top of his deck?” (Sample from the Queen’s University / ATR Labs X-ray Film Database)

Vocal fold vibration [UCLA Phonetics Lab demo]

Places of articulation labial dental alveolar post-alveolar/palatal velar uvular pharyngeal laryngeal/glottal

Articulatory parameters for English consonants (in ARPAbet) MANNER OF ARTICULATION VOICING: voiced voiceless

American English vowel space FRONTBACK HIGH LOW ey ow aw oy ay iy ih eh ae aa ao uw uh ah ax ixux

Acoustic landmarks “Patricia and Patsy and Sally” [p][t][p][t] [p][t] [l][sh][s] [n] [ix] [ih] [ax][ae][iy] [ae]

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

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.in context –simple rules: /{t,d}/ --> [  V’ _ V –FSA’s, FST’s –declarative constraints: t:  V’ _ V

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.

Application: Word Pronunciation for TTS Pronouncing dictionaries (the: [‘dhax],[‘dhiy]) Problems: –Homographs (bass/bass, wind/wind, desert/desert) –Abbreviation (dr., st.) –Numbers ( ) –Acronyms (NAACL, IDIAP) –Morphological variation (unrelentingly) –Proper names and unknown words rules + dictionaries/dictionaries + rules

Hybrid model: –FSTs model individual word pronunciation in lexicon (e.g. reg-noun-stem entry c:k a:ae t:t) –FSAs model morphology (e.g. reg-noun-stem + s) –FSTs for pronunciation rules (e.g. s--> z) –special rules to model name and acronym pronunciation –default letter2sound rules for other words

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?

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 5