Statistical NLP Spring 2011 Lecture 4: Speech Recognition Dan Klein UC Berkeley Speech in a Slide Frequency gives pitch; amplitude gives volume s
amplitude ee ch l a
b Frequencies at each time slice processed into observation vectors frequency p
..a12a13a12a14a14.. Articulatory System Nasal cavity Oral cavity Pharynx Vocal folds (in the larynx) Trachea Lungs Sagittal section of the vocal tract (Techmer 1880)
Text from Ohala, Sept 2001, from Sharon Rose slide Places of Articulation alveolar dental labial post-alveolar/palatal velar uvular pharyngeal
laryngeal/glottal Figure thanks to Jennifer Venditti Labial place labiodental bilabial Bilabial: p, b, m
Labiodental: f, v Figure thanks to Jennifer Venditti Coronal place alveolar dental post-alveolar/palatal Dental:
th/dh Alveolar: t/d/s/z/l/n Post: sh/zh/y Figure thanks to Jennifer Venditti Dorsal Place Velar:
k/g/ng velar uvular pharyngeal Figure thanks to Jennifer Venditti Space of Phonemes Standard international phonetic alphabet (IPA) chart of consonants
Manner of Articulation In addition to varying by place, sounds vary by manner Stop: complete closure of articulators, no air escapes via mouth Oral stop: palate is raised (p, t, k, b, d, g) Nasal stop: oral closure, but palate is lowered (m, n, ng) Fricatives: substantial closure, turbulent:
(f, v, s, z) Approximants: slight closure, sonorant: (l, r, w) Vowels: no closure, sonorant: (i, e, a) Space of Phonemes Standard international phonetic alphabet (IPA) chart of consonants Vowel Space
She just had a baby What can we learn from a wavefile? No gaps between words (!) Vowels are voiced, long, loud Length in time = length in space in waveform picture Voicing: regular peaks in amplitude When stops closed: no peaks, silence Peaks = voicing: .46 to .58 (vowel [iy], from second .65 to .74 (vowel [ax]) and so on Silence of stop closure (1.06 to 1.08 for first [b], or 1.26 to 1.28 for second
[b]) Fricatives like [sh]: intense irregular pattern; see .33 to .46 Non-Local Cues pat
pad bad spat Example from Ladefoged Simple Periodic Waves of Sound 0.99
0 0.99 0 0.02 Time (s) Y axis: Amplitude = amount of air pressure at that point in time Zero is normal air pressure, negative is rarefaction
X axis: Time. Frequency = number of cycles per second. 20 cycles in .02 seconds = 1000 cycles/second = 1000 Hz Complex Waves: 100Hz+1000Hz 0.99 0 0.9654 0
0.05 Time (s) Spectrum Amplitude Frequency components (100 and 1000 Hz) on x-axis 100
Frequency in Hz 1000 Spectrum of an Actual Soundwave 40 20
0 0 5000 Frequency (Hz) Part of [ae] waveform from had Note complex wave repeating nine times in figure Plus smaller waves which repeats 4 times for every large
pattern Large wave has frequency of 250 Hz (9 times in .036 seconds) Small wave roughly 4 times this, or roughly 1000 Hz Two little tiny waves on top of peak of 1000 Hz waves Back to Spectra Spectrum represents these freq components Computed by Fourier transform, algorithm which separates out each frequency component of wave.
x-axis shows frequency, y-axis shows magnitude (in decibels, a log measure of amplitude) Peaks at 930 Hz, 1860 Hz, and 3020 Hz. Why these Peaks? Articulator process: The vocal cord vibrations create harmonics The mouth is an amplifier Depending on shape of mouth, some harmonics
are amplified more than others Vowel [i] sung at successively higher pitches F#2 A2 C3 F#3
A3 C4 (middle C) A4 Figures from Ratree Wayland Resonances of the Vocal Tract The human vocal tract as an open
tube: Closed end Open end Length 17.5 cm. Air in a tube of a given length will tend to vibrate at resonance frequency of tube. Constraint: Pressure differential should be maximal at (closed)
glottal end and minimal at (open) lip end. Figure from W. Barry From Sundberg Computing the 3 Formants of Schwa Let the length of the tube be L F1 = c/1 = c/(4L) = 35,000/4*17.5 = 500Hz F2 = c/2 = c/(4/3L) = 3c/4L = 3*35,000/4*17.5 = 1500Hz F3 = c/3 = c/(4/5L) = 5c/4L = 5*35,000/4*17.5 = 2500Hz
So we expect a neutral vowel to have 3 resonances at 500, 1500, and 2500 Hz These vowel resonances are called formants From Mark Libermans Web site Seeing Formants: the Spectrogram
Vowel Space How to Read Spectrograms bab: closure of lips lowers all formants: so rapid increase in all formants at beginning of "bab dad: first formant increases, but F2 and F3 slight fall gag: F2 and F3 come together: this is a characteristic of velars. Formant transitions take longer in velars than in alveolars or labials
From Ladefoged A Course in Phonetics She came back and started again 1. 3. 4. 5. 6. 7. 8.
9. lots of high-freq energy closure for k burst of aspiration for k ey vowel; faint 1100 Hz formant is nasalization bilabial nasal short b closure, voicing barely visible. ae; note upward transitions after bilabial stop at beginning note F2 and F3 coming together for "k" From Ladefoged A Course in Phonetics
Kinetic Theory of Gases II Mean Free Path l: average distance between two consecutive collisions the more molecules the more collisions the bigger the molecules the more collisions Definition: For constant volume: For constant pressure: The 1st Law of Thermodynamics:...
Some numbers - UK Boscastle 2004 Boscastle 2004 Boscastle 2004 Slide 10 Ulley Dam - 2007 Brazil 2008 Typical Applications of ISIS in the UK ISIS 1D - Modelling Channels and Structure A typical ISIS river Section Weirs & Spills...
Lecture 2 Types of Rates Treasury rates LIBOR rates Euribor rates Zero Rates A zero rate (or spot rate), for maturity T, is the rate of interest earned on an investment that provides a payoff only at time T Example...
Crime is a punishable offense against society. When a crime occurs, society (acting through police and prosecutors) attempts to identify, arrest, prosecute, and punish the criminal. These efforts are designed to protect society
Indirect Cost Participants may charge eligible direct and indirect costs Reimbursement of indirect costs: For all: either actual overhead, or simplified method, or flat rate of 20% of direct costs For Non profit Public Bodies, Secondary and Higher Education establishments,...
The Brillouin Zone. Is defined as the Wigner-Seitz primitive cell in the reciprocal lattice (smallest unique set of distance/area/volume in reciprocal space). Its construction exhibits all the wavevectors. k. which can be Bragg-reflected by the crystal. Also critical for understanding...
In your design, consider whether the client should really be able to specify full XML messages (including DTDs) Ideally, disallow DTDs in user-specified XML. Configure XML parsers to limit DTD entity expansion, and in general, XML entity depth. Newer Java...