SPEECH RECOGNITION 2 DAY 15 – SEPT 30, 2013 Brain & Language LING 4110-4890-5110-7960 NSCI 4110-4891-6110 Harry Howard Tulane University.

Slides:



Advertisements
Similar presentations
A. Hatzis, P.D. Green, S. Howard (1) Optical Logo-Therapy (OLT) : Visual displays in practical auditory phonetics teaching. Introduction What.
Advertisements

Tom Lentz (slides Ivana Brasileiro)
Normal Aspects of Articulation. Definitions Phonetics Phonology Articulatory phonetics Acoustic phonetics Speech perception Phonemic transcription Phonetic.
SYNTAX 4 DAY 33 – NOV 13, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
DISORDERS OF AUDITORY PROCESSING DAY 21 – OCT 15, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
Sounds that “move” Diphthongs, glides and liquids.
SPPA 403 Speech Science1 Unit 3 outline The Vocal Tract (VT) Source-Filter Theory of Speech Production Capturing Speech Dynamics The Vowels The Diphthongs.
Human Speech Recognition Julia Hirschberg CS4706 (thanks to John-Paul Hosum for some slides)
DISORDERS OF AUDITORY PROCESSING 1 DAY 20 – OCT 14, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
From Resonance to Vowels March 8, 2013 Friday Frivolity Some project reports to hand back… Mystery spectrogram reading exercise: solved! We need to plan.
Basic Spectrogram & Clinical Application Lab 9. Spectrographic Features of Vowels n 1st formant carries much information about manner of articulation.
JPN494: Japanese Language and Linguistics JPN543: Advanced Japanese Language and Linguistics Phonology & Phonetics (2)
NEUROANATOMY OF LANGUAGE 4 DAY 12 – SEPT 23, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
ASPECTS OF LINGUISTIC COMPETENCE 3 SEPT 06, 2013 – DAY 5 Brain & Language LING NSCI Harry Howard Tulane University.
English Phonetics and Phonology Presented by Sergio A. Rojas.
SPEECH RECOGNITION 1 DAY 14 – SEPT 27, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
ASPECTS OF LINGUISTIC COMPETENCE 5 SEPT 11, 2013 – DAY 7 Brain & Language LING NSCI Harry Howard Tulane University.
INTRODUCTION TO THE COURSE AUG. 26, DAY 1 Brain & Language LING 4110/4890/5110/7960? NSCI 4110/4891/6110 Fall 2013.
WORD SEMANTICS 1 DAY 26 – OCT 28, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
SPEECH PERCEPTION 2 DAY 17 – OCT 4, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
SYNTAX 7 ON-LINE PROCESSING DAY 36 – NOV 20, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
SYNTAX 9 AGRAMMATISM DAY 38 – NOV 25, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
PHONETICS AND PHONOLOGY
ASPECTS OF LINGUISTIC COMPETENCE 2 SEPT 04, 2013 – DAY 4 Brain & Language LING NSCI Harry Howard Tulane University.
Basic Spectrogram Lab 8. Spectrograms §Spectrograph: Produces visible patterns of acoustic energy called spectrograms §Spectrographic Analysis: l Acoustic.
Speech Perception Overview of Questions Can computers perceive speech as well as humans? Does each word that we hear have a unique pattern associated.
Speech sounds Articulation.
SYNTAX 5 ON-LINE PROCESSING DAY 34 – NOV 15, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
SYNTAX 1 DAY 30 – NOV 6, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
LATERALIZATION OF PHONOLOGY DAY 22 – OCT 18, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
SPEECH PERCEPTION The Speech Stimulus Perceiving Phonemes Top-Down Processing Is Speech Special?
Introduction to Speech Production Lecture 1. Phonetics and Phonology Phonetics: The physical manifestation of language in sound waves. –How sounds are.
MODULARITY DAY 13 – SEPT 25, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
Articulation and Description of English Vowels
SPEECH RECOGNITION LEXICON DAY 19 – OCT 9, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
Phonetics and Phonology
Phonological Constraints on the Acquisition of Mid Vowels in English for Students in Taiwan author: 黃俐雯 presented by Lisa Liu 報告人: 劉莉莎.
SYNTAX 8 ON-LINE PROCESSING DAY 37 – NOV 22, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
WORD SEMANTICS 4 DAY 29 – NOV 4, 2011 Brain & Language LING NSCI Harry Howard Tulane University.
1 Speech Perception 3/30/00. 2 Speech Perception How do we perceive speech? –Multifaceted process –Not fully understood –Models & theories attempt to.
Morphology & the mental lexicon DAY 25 – Oct 25, 2013
ASPECTS OF LINGUISTIC COMPETENCE 4 SEPT 09, 2013 – DAY 6 Brain & Language LING NSCI Harry Howard Tulane University.
SYNTAX 2 DAY 31 – NOV 08, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
SPEECH PERCEPTION DAY 16 – OCT 2, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
Speech Science IX How is articulation organized? Version WS
LATERALIZATION OF PHONOLOGY 2 DAY 23 – OCT 21, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
SPEECH PERCEPTION DAY 18 – OCT 9, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
SYNTAX 6 ON-LINE PROCESSING DAY 35 – NOV 18, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
Speech Science VI Resonances WS Resonances Reading: Borden, Harris & Raphael, p Kentp Pompino-Marschallp Reetzp
Public service announcement What is a Ponzi scheme? How is the passive voice formed? (someone) ended the Ponzi scheme quickly. AGENT THEME The Ponzi scheme.
Artificial Intelligence 2004 Speech & Natural Language Processing Speech Recognition acoustic signal as input conversion into written words Natural.
Unit 5 Phonetics and Phonology. Phonetics Sounds produced by the human speech organs are called the “phonic/auditory medium” Phonetics is the study of.
AUDITORY TRANSDUCTION SEPT 4, 2015 – DAY 6 Brain & Language LING NSCI Fall 2015.
ARTIFICIAL INTELLIGENCE FOR SPEECH RECOGNITION. Introduction What is Speech Recognition?  also known as automatic speech recognition or computer speech.
AUDITORY CORTEX 4 SEPT 21, 2015 – DAY 12 Brain & Language LING NSCI Fall 2015.
THE FIELDS OF LINGUISTICS AUG. 26, 2015 – DAY 2 Brain & Language LING NSCI Fall 2015.
Stop + Approximant Acoustics
AUDITORY CORTEX 1 SEPT 11, 2015 – DAY 8 Brain & Language LING NSCI Fall 2015.
Acoustic Phonetics 3/14/00.
Speech 1 Sept 11, 2017 – DAY 6 Brain & Language
Speech 2 Sept 13, 2017 – DAY 7 Brain & Language
Vowels and Consonant Serikova Aigerim.
Week 4 – English Vowels Monophthongs Diphthongs Triphthongs One sound
Introduction to Linguistics
Articulation and Description of English Vowels
Phonetics.
Chapter 2 Phonology.
عمادة التعلم الإلكتروني والتعليم عن بعد
Motor theory.
What is phonetics? It is the study of the production, transmission and reception of speech sounds. It studies the medium of the spoken language. It looks.
Presentation transcript:

SPEECH RECOGNITION 2 DAY 15 – SEPT 30, 2013 Brain & Language LING NSCI Harry Howard Tulane University

Course organization The syllabus, these slides and my recordings are available at If you want to learn more about EEG and neurolinguistics, you are welcome to participate in my lab. This is also a good way to get started on an honor's thesis. The grades are posted to Blackboard. 9/30/13Brain & Language, Harry Howard, Tulane University 2

REVIEW 9/30/13Brain & Language, Harry Howard, Tulane University 3

Review Pitch shows fundamental frequency (F 0 ) Spectrogram shows formants (F 1-3 ) Sound wave 9/30/13Brain & Language, Harry Howard, Tulane University 4

SPEECH RECOGNITION Ingram §5 9/30/13Brain & Language, Harry Howard, Tulane University 5

use Praat in class 9/30/13Brain & Language, Harry Howard, Tulane University 6

9/30/13Brain & Language, Harry Howard, Tulane University 7 Vowel articulation Tongue height: high, (mid), low put your hand under your jaw and say the vowel of: mat, met, mate, mitt, meat meat, mitt, mate, met, mat Tongue advancement: front, central, back Lip configuration: rounded, neutral, retracted

9/30/13Brain & Language, Harry Howard, Tulane University 8 Vowel description FrontCentralBack High iɪiɪ uʊuʊ (Mid) eɛeɛ ɝəɚʌɝəɚʌ oɔoɔ Low æa RetractedNeutralRounded

Sample vowel spectrograms 9/30/13Brain & Language, Harry Howard, Tulane University 9 Wide band spectrograms of the vowels of American English in a /b__d/ context. Top row, left to right: [i, ɪ, e ɪ, ɛ, æ]. Bottom row, left to right: [ ɑ, ɔ, o, ʊ, u].

Acoustic cues and distinctive features Three problems a. Input signal b. Internal representation c. Interface between (a)and (b) Lexical information retrieval but we only need the phonological form of a lexical item 9/30/13Brain & Language, Harry Howard, Tulane University 10

Why speech recognition is difficult The segmentation problem The variability problem coarticulation The speaking environment Speakers’ vocal tracts Speech rate and style Rate of information transmission 9/30/13Brain & Language, Harry Howard, Tulane University 11

Lexical retrieval Speech perception involves phonological parsing prior to lexical access It is not enough to know the lexicon beforehand. Phonetic forms and phonological representations Speech/speaker normalization Distinctive features and acoustic cues Underspecified vs. fully specified Discrete vs. continuous Hierarchical organization vs. entrainment 9/30/13Brain & Language, Harry Howard, Tulane University 12

NEXT TIME Finish Ingram §6. ☞ Go over questions at end of chapter. 9/30/13Brain & Language, Harry Howard, Tulane University 13