Automatic Speech Recognition (ASR): 2014/15

[course descriptor]

Lecturers


News

Reading

Textbook

Review and Tutorial Articles

Syllabus 2014/15

Lecture No.DateWeekLecturerTopic and slidesReading
1Mon 12 January 1RenalsIntroduction to Speech Recognition (slides) J&M: chapter 7, chapter 9 (9.1 - 9.3)
R&H review chapter
2Thu 15 January 1ShimodairaSpeech Signal Analysis 1 (slides) J&M: Sec 9.3
Taylor, chapters 10, 12
3Mon 19 January 2ShimodairaSpeech Signal Analysis 2 Hermansky (1990), PLP analysis of speech
4 Thu 22 January 2 ShimodairaAcoustic modelling basics: HMMs and GMMs 1 (slides-6up,slides) J&M: Secs 6.1-6.5, 9.2, 9.4
G&Y review
R&H review chapter
Rabiner & Juang (1986) Tutorial
5Mon 26 January 3ShimodairaAcoustic modelling basics: HMMs and GMMs 2
Mon 26 January 3RenalsTutorial / Group 1
Wed 28 January 3RenalsTutorial / Group 2
6Thu 29 January 3RenalsContext-dependent phone modelling with HMMs 1 (slides) Young (2008)
Lee (1990) Context-dependent phonetic hidden Markov models for speaker-independent continuous speech recognition
Thu 29 January 3RenalsTutorial / Group 3
7Mon 2 February 4RenalsContext-dependent phone modelling with HMMs 2 Young & Woodland (1994) State clustering in hidden Markov model-based continuous speech recognition
Young et al (1994). Tree-based state tying for high accuracy acoustic modelling,
Thu 5 February 4ShimodairaIntroduction to Assignment 1 Assignment 1: continuous speech recognition
Thu 5 February 4Lab session (17:00)
8Mon 9 February 5RenalsLexicon and language model (slides) J&M, Ch 4
Manning & Schutze, Ch 6
Mon 9 February 5Lab session (17:00)
Wed 11 February 5Lab session (17:00)
9Thu 12 February 5RenalsSearch and decoding (slides) Aubert (2002) An overview of decoding techniques for large vocabulary continuous speech recognition
Thu 12 February 5Lab session (17:00)
Mon 16 February 6 No Lecture - Innovative Learning Week
Thu 19 February 6 No Lecture - Innovative Learning Week
10Mon 23 February 7Shimodaira Intro to neural networks (slides)
Multi-layer neural networks note
Morgan & Bourlard (1995), Continuous speech recognition: An introduction to the hybrid HMM/connectionist approach
Nielsen, Neural Networks and Deep Learning
Mon 23 February 7Lab session (17:30)
Wed 25 February 7Assignment 1 Deadline (16:00)
11Thu 26 February 7Renals(Deep) neural network acoustic models (slides) Hinton et al (2012), Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups
12Mon 2 March 8Renals Neural network language models (slides)Bengio et al (2006), Neural probabilistic language models(Secs 6.1, 6.2, 6.3, 6.7, 6.8)
Mikolov et al (2011), Extensions of recurrent neural network language model
Mon 2 March 8RenalsTutorial / Group 1
Wed 4 March 8RenalsTutorial / Group 2
13Thu 5 March 8RenalsSpeaker adaptation 1 (slides) G&Y review, sec. 5
Woodland (2001), Speaker adaptation for continuous density HMMs: A review
Thu 5 March 8RenalsTutorial / Group 3
14Mon 9 March 9RenalsSpeaker adaptation 2
Wed 11 March 9Assignment 2 Deadline (16:00)
15Thu 12 March 9Peter BellGuest lecture: Transcribing TED talks (slides)
Mon 16 March 10No lecture
Thu 19 March 10RenalsWrap-up session

Schedule

Closer to the exam we are very happy to arrange a revision lecture at a time convenient to everyone. The point of this lecture will be to answer and discuss any questions about the course.

Coursework

There are two pieces of coursework.

  1. Assignment 1: continuous speech recognition - monophone and triphone models. The coursework will involve training and testing a continuous speech recognition system using the HTK software. We'll use the WSJCAM0 database (British English recordings of speakers reading the Wall Street Journal sentences).
    Released: Monday 2 February 2015
    Deadline: Wednesday 25 February 2015, 16:00
    Feedback: Wednesday 11 March 2015
    Report templates: Q and A
  2. Assignment 2: literature review. Choose one of the following topics.

    Released: Thursday 26 February 2015
    Deadline: Wednesday 11 March 2015, 16:00
    Feedback: Wednesday 25 March 2015
    Report templates:

School of Informatics coursework policies:

Software tools


 
 
 


Home : Teaching : Courses : Asr 

Informatics Forum, 10 Crichton Street, Edinburgh, EH8 9AB, Scotland, UK
Tel: +44 131 651 5661, Fax: +44 131 651 1426, E-mail: school-office@inf.ed.ac.uk
Please contact our webadmin with any comments or corrections. Logging and Cookies
Unless explicitly stated otherwise, all material is copyright © The University of Edinburgh