Last Modified : Fri, 19 Apr 19
ECE537-F18
- ECE-537: Fundamentals of Speech Processing UIUC; ; Description; UIUC 2018 Academic Calendar; First day video
- Website Fall Daily schedule
- Professor: Jont Allen
- Time: 12-12:50 MWF; Location: 3013 ECEB(1.135)
- Textbook pdf (2014); An Invitation to MathPhysics pdf; Course description; About the final; Exam I
- Office Hours: Tu 3PM, Fri 3 PM; Location: 5034 ECEB
- This week's schedule
- Final grade summary and analysis pdf
ECE 537 Schedule (Fall 2018)
| L | W | D | Date | Lecture & Assignment |
| Part I: Acoustics/VT modeling/Signal processing (20 Lectures) | ||||
| 1 | 35 | M | 8/27 | Introductions. Lecture: Overview: Speech production, Acoustics, Psychophysics, neural and information processing. Entropy: Its meaning, definition and the intuition behind it; Read: Flanagan, Chapt. 1: of pdf (2014) |
| 2 | W | 8/29 | Lecture: Mechanisms of Speech production: Sounds of speech: Vowels and consonants; Read: Chapter 2 pdf (2014) HW-1: Basic Acoustics (due 1 week) (HW-1) | |
| 3 | F | 8/31 | Lecture: Pressure, volume velocity, impedance. Intensity, speech power; sound level; dB, dB-SPL | |
| - | 36 | M | 9/3 | Labor Day Holiday -- No class |
| 4 | W | 9/5 | Lecture: 1D wave equation; Acoustic Transmission lines; Matrix formulations; Vowels, Formants; Helmholtz resonator, ABCD-Transmission (Chain) matrix; Conversion table for 2-ports (pdf) Read: Flanagan, Ch. 2.2 HW-1 due HW-2: TL and reflectance (due 1 week) HW-2,Transmission line simulation program txline.m | |
| 5 | 2 | F | 9/7 | Lecture: Solution of 1-D transmission line equation: Lip radiation impedance, The Helmholtz resonator Read: Flanagan, Chapter 3: 3.1-3.2 pdf (2014) |
| 6 | 37 | M | 9/10 | Lecture:d'Alembert solutions for 1-D and 3-D transmission lines; Sound propagation in tubes in speech production; Introduction to reflectance; Read: Wave model of the Cat eardrum, Parent and Allen 2007 pdf), 2010 Human ear canal pdf, ; Review: Octave/Matlab filter design techniques: bilinear Z, FIR, IIR |
| 7 | W | 9/12 | Lecture: Transmission Lines with complex loads and the Propagated Reflectance; Text: Flanagan, Ch. VI (Sect. 6.262, pp 272-276); Readings: Wave digital filters (Bilbao PhD Thesis p. 1-15) (pdf) HW-2 due; HW-3: TLs with complex terminations due in two weeks) Simulation of the middle ear:'' (HW-3), txline.m, gamma.m | |
| 8 | F | 9/14 | Lecture:Impedance and reflectance at a tube junction (Karal correction pdf), and half-sphere (the mouth) Text: Ch. 3, Sec. 3.3, pages 136-152 | |
| 9 | 38 | M | 9/17 | Lecture: 2-port networks; Read: Bilabo Thesis (page 14: pdf);Text Chap. 3, sect. 3.8.1 pages 31-34 radiation impedance load; Review: Rosowski, Carney and Peak (1988) on the cat middle ear pdf; Background material: Guinan and Peak pdf; Lynch et al. 1982 pdf |
| 10 | W | 9/19 | Lecture: cont. 2-port and the 3-port nasal tract; Network Postulates pdf; Conversion tables for 2-portsOptional Read:Thevenin (pdf),Norton (pdf) Read:Peterson and Barney (1952) djvu and Peterson (1952) djvu | |
| 11 | F | 9/21 | Lecture: Horn Radiation Impedance; Karal Correction; ABCD Transmission matrix method; Bernoulli's equation Text: Flanagan pp 41-53; Read: vanDen Berg (1957) djvu | |
| 12 | 39 | M | 9/24 | Lecture: 'Signal processing:' Fourier Series, Fourier Transform, Laplace Transform, ZT, DTFT, DFT, FFT |
| 13 | W | 9/26 | Lecture: Cepstral analysis; HW-3 Due HW-4: Vocal-Tract Simulation: Due in three weeks (HW-4, Octave/Matlab m files) | |
| 14 | F | 9/28 | Lecture: History of acoustics
BC: Pythagoras; Aristotle; | |
| 15 | 40 | M | 10/1 | Lecture: Review HW-1, HW-2, HW-3; The glottal oscillator & Bernoulli's (, , ) Read: Flanagan Sec. 3.74 pages 69-72 |
| 16 | W | 10/3 | Lecture: Linear prediction of speech; Read: Flanagan Sec. 8.112, pp 372-376; Sec. 8.13, pp 390-395; Atal and Hanauer (1971) pdf, | |
| 17 | F | 10/5 | Lecture: 'STFT window methods; STFT for speech processing with analysis/synthesis; Inverse STFT; pdf, pdf,Reading spectrograms: class-room exercises Read: Flanagan Chap. 8, pp 361-363; | Begin writing your Final exam: Part I;]] | |
| - | 41 | M | 10/8 | No office hours; Optional class: Discuss of Exam; No class due to|Exam I: 7-10 PM; 2013 ECEB]] NO CRIB SHEETs |
| Part II: Psychoacoustics (10 Lectures) | ||||
| 18 | W | 10/10 | Lecture: Room acoustics; point source; 1, 2 and 6 wall Image method; Wall reflection coef. for finite impedance walls: (pdf) | |
| 19 | F | 10/12 | Lecture: Special Guest Lecture on Digital Speech Coding/compression, Lec 19 Prof. Mark Hasagawa-Johnson | |
| 20 | 42 | M | 10/15 | Lecture: Music, speech and audio compression coding (MPEG) Read:Text book chapters (Atal) pdf; \(\mu\)-Law speech coding pdf; Music coding methods pdf |
| 21 | W | 10/17 | Lecture: Psychoacoustics I: Internal noise model of the JND Riesz pure-tone intensity JND (1928) Masking: Weber's and Fechner's Law; Intensity JND and the near-miss; 'Psychoacoustics II:' Introduction to loudness, Steven's Law; Loudness Lecture notes (Allen): pdf Read: Flanagan Chapter 4 (pdf), Allen Review (pages 20-30) pdf, Fletcher and Munson (1933) (pp 82-94) pdf HW-4 due HW-5: LPC (Due 1 week Atal 71, (HW-5, Speech samples) | |
| 22 | F | 10/19 | Lecture: Cochlear Physiology I: Middle ear and inner ear (Cochlear) anatomy, basilar membrane, 1D Models, Hair cells, Nonlinear basilar membrane; Frequency JND, semitone, Internal noise and Masking; relation between the intensity and frequency JND (Cochlear frequency response and the slope of the tuning curve); Read: Review of Cochlear Modeling: Part II (pp 19-28): pdf; page 151(166)-155(170) of Fletcher's 1929 Book pdf MIT/HST-725: The auditory system pdf | |
| 23 | 43 | M | 10/22 | Lecture: Cochlear Physiology II: traveling waves, neural tuning curves, critical bands, hair cells, neural masking, Upward spread of masking; Forward masking; Auditory Pathway I: Neural Tuning Read: Review of Cochlear Modeling (pp 1-19) (pdf) |
| 24 | W | 10/24 | Lecture: Cochlear Physiology III: Micromechanics, OHC, IHC Lecture Notes (pdf): Modeling the Cochlea and Organ of Corti, and Read: Wegel and Lane (1924), Part II (pdf) HW-5 due HW-6: Radial waves/STFT/OLA/Speech coding (Due in 2 weeks) (HW-6), speech files) | |
| 25 | F | 10/26 | Lecture: Psychoacoustics III: Relations between Psychophysics and the cochlea; Greenwood's place-map function Read: Review of Cochlear Modeling (pp 1-19) (pdf), Part I; Fletcher and Munson (1933) (pp 82-94) (pdf) | |
| 26 | 44 | M | 10/29 | Lecture: Cochlear Critical bands Read:'Harvey Fletcher's role ...' (not the section on the Articulation Index (AI)) pdf |
| 27 | W | 10/31 | Lecture: Cochlear Physiology IV: The nonlinear Cochlea; The upward spread of masking (USM) and 2-tone suppression (2TS) Supplement: The Auditory Nerve (pdf), Fahey Allen (1997) neural masking (pdf) Read: Features in speech Allen and Li, (2010) (pdf) | |
| 28 | F | 11/2 | Lecture: Prof. Wickesberg, Part I: The central auditory system; Neural signal and the Auditory Pathway; SankaranMicheylKalluriCarlile (pdf) | |
| 29 | 45 | M | 11/5 | Lecture: Prof. Wickesberg, Auditory Pathway (AN+CN), KalluriJCNS-I (pdf, Part II; KalluriJCNS-II pdf) |
| 30 | W | 11/7 | Lecture: Prof. Wickesberg, Auditory Pathway (AN+CN): Part III: (pdf, pptx) HW-6: Due HW-7: Simulated Green eggs and ham or As You Like it (HW-7, AULI+GEnH.tgz) Due after break | |
| Part III: Human Speech Recognition/Information Processing (10 Lectures) | ||||
| 31 | F | 11/10 | Lecture: Information theory I: Information, Entropy, Relative Entropy; Channel Capacity Gentle introduction to IT: (slides) Read: Pierce, JR ''Early days of Information Theory (pdf) | |
| 32 | 46 | M | 11/12 | Lecture: Information theory II: Morse code example Shannon Channel Read: pp 1-10 Shannon (1948) (pdf I, pdf III, pdf 1950) |
| 33 | W | 11/14 | Lecture: Information theory III:; Entropy, Relative Entropy, Markov models, State diagram; Read: Shannon (1950) (pdf) and this video | |
| 34 | F | 11/16 | Lecture: EM algorithm: Example: Speech and noise separation Read: French and Steinberg (1947) (pdf); Good-Turing djvu Discussion of the EM alg. with examples | |
| - | 48 | - | - | Thanksgiving Holiday (11/17-11/26) |
| 35 | 47 | M | 11/26 | Lecture: Articulation Index/Speech Transmission Index/Speech Intelligibility Index;
Support material: RV Shannon et al (1995) pdf; |
| 36 | W | 11/28 | Lecture: STI/SII Read: Steeneken & Houtgast (1980) Speech Transmission Index (djvu) and Houtgast (1989) Modulation detection (djvu) | |
| 37 | F | 11/30 | Lecture: Human speech recognition (HSR), Articulation Index (AI), average score: \(P_c(A) = 1-e_{chance} e_{min}^{AI}\) The confusion matrix (CM), maximum entropy syllable error models, etc.; Allen notes (pdf) Read: Continue with French and Steinberg (1947) pdf;Miller Nicely (1955) pdf;Miller Nicely confusions as a function of the articulation index; entropy, grouping and chance pdf DUE: Preliminary version of your Final Exam, for review | |
| - | 49 | M | 12/3 | Lecture: Review for Exam II Assignment:: Turn in draft of final paper for review by Allen |
| 38 | W | 12/5 | Exam II: (NO CLASS) Psychoacoustics, Physiology, Speech, LPC, AI, Historical items Room: 3020 ECEB; Time: 7-9:30 PM; Grade Distribution pdf Assignment: Work on Final exam | |
| 39 | F | 12/7 | Lecture: Effects of language and semantic context Miller (1962) djvu, Boothroyd (1988) pdf; Allen Notes: Events and the AI (pdf) Read: Miller, Heisen and Lichten (1951) (pdf) | |
| 40 | 50 | M | 12/10 | Lecture: Language context models, cont., Bronkhorst93 Read: W. Li Random texts exhibit Zipf's-Law djvu |
| 41 | W | 12/12 | Assignment: Work on final exam; Course Review; Final paper Prep; | |
| - | R | 12/14 | Reading Day | |
| - | 51 | M | 12/14-19 | [Final paper Due before or on Dec 19] The final is a 15-25 page paper, written in the style and format (but single column) of a journal paper, that discusses everything that you have learned in this course. Writing style, spelling, figures, labels of figures, are all part of the grade. Allen's Grading of the final: The final is graded based on a list of all the topics that are covered. If there is a paragraph that discusses each topic on my list, then you get at least 1 point, and if the discussion covers the topic effectively, you can get up to 5 points. There are at least 20 topics on the list. When you get to 100 points, you get an A+ on the exam. I expect that you draw on the homework as a starting point. Don't just dump the homework into the exam without modification, that wont get you points. Don't just dump a large number of unexplained figures (that you got from someone else for example) and expect to get points. I need words around each figure. I am looking for insightful comments that link the material together. Your comments on the relevance of each of the topics I covered in this course, homework problems, exams, etc., are welcome. No points will be taken off, nor given, for strong opinions on my teaching style, or lack thereof, organization, or lack thereof, etc. Please put all such comments in a discussion section at the end of the paper, isolated from the rest of the material. To deposit the final paper, place a copy in my Beckman mailbox, and send me the pdf. |
| - | - | - | Not proofed beyond here |
Powered by PmWiki