University Homepage School Homepage School Contacts School Search

Automatic Speech Recognition (ASR) -2011/12-

[course descriptor]

Lecturer

News

• FAQ time will be arranged in AT-4.12. See the assignment section for details.
• The first lecture: Monday, 16th January 2012, 15:00-15:50
  
• In addition to "Speech Processing" as the pre-requisite course, it would be advantageous that you take either "Introductory Applied Machine Learning" (IAML), or "Probabilistic Modelling and Reasoning" (PMR) in advance. "Machine Learning and Pattern Recognition" (MLPR) and "Machine Translation" (MT) are related second semester courses, along with the PPLS course on "Speech Synthesis".
• You can have a look at the last year's couse web page

Schedule

• The lectures will be held on Mondays and Thursdays at 15:00-15:50 (in Semester 2) at AT-2.14 (lectures) or AT-4.12 (lab).

Schedule

• NB: the following schedule is provisional and subject to change.

Week	Monday (----)		Thursday (---)
1	16.Jan	Signal analysis (HS)	19.Jan	Signal analysis (HS)
2	23.Jan	Statistical PR (HS)	26.Jan	LAB[AT4.12] (HS)
3	30.Jan	Statistical PR (HS)	02.Feb	HMMs 1 (HS)
4	06.Feb	HMMs 2 (HS)	09.Feb	LAB[AT4.12] (HS)
5	13.Feb	Modelling speech with HMMs 1 (HS)	16.Feb	Modelling speech with HMMs 2 (HS)
6	20.Feb	(no lecture)	23.Feb	(no lecture)
7	27.Feb	Lexicon and language model (HS)	01.Mar	LAB[AT4.12] (HS)
8	05.Mar	Search and decoding (HS)	08.Mar	LAB[AT4.12] (HS)
9	12.Mar	Speaker adaptation 1 (HS)	15.Mar	LAB[AT4.12] (HS)
10	19.Mar	Speaker adaptation 2 (HS)	22.Mar	Discrimination and feature combination (HS)
11	26.Mar	Environmental robustness (HS)	29.Mar	Case study

Assignment

• The submission deadline is Thursday, 5th April 2012 at 16:00.
• See the instructions in the handout for lab-session(3).
• Report templates (LaTeX) (MS Word)
• FAQ
• QandA for the assignment will be available in AT-4.12 as follows

  Date	Time
  Thursday 22 March	17:00-18:00
  Wednesday 28 March	17:00-18:00
  Friday 30 March	18:00-18:30
  Monday 02 April	17:00-18:00
  Tuesday 03 April	17:00-18:00
  Wednesdy 04 April	17:00-17:30

Handouts

• Lecture 1 and 2 (16, 19 Jan): signal analysis handout (1)
• Lecture 3 and 4: Statistical pattern recognition handout (2)
• Lecture 5 and 6: Hidden Markov Models handout (3) [updated on 15/Feb]
• Lecture 7 and 8: Modelling speech with HMMs handout (4) [updated on 16/Feb]
• Lecture 9: Lexicon and language model (Words: Pronunciations and Language Models) handout (5)
• Lecture 10: Search and decoding handout (6)
• Lecture 11 and 12: Speaker adaptation handout (7)
• Lecture 13: Discrimination and feature combination handout (8)
• Lecture 14: Environmental robustness handout (9)
• Lecture 15: The AMI-ASR meeting recognition system handout (10)

• lab-session (1)
• lab-session (2)
• lab-session (3)
• lab-session (4) (revised on 02/04)
• lab-session (5)

References

• Useful texts