Lecture No. | Date | Week | Lecturer | Topic and slides | Reading |
1 | Mon 12 January | 1 | Renals | Introduction to Speech Recognition (slides) | J&M: chapter 7, chapter 9 (9.1 - 9.3) R&H review chapter |
2 | Thu 15 January | 1 | Shimodaira | Speech Signal Analysis 1 (slides) | J&M: Sec 9.3 Taylor, chapters 10, 12 |
3 | Mon 19 January | 2 | Shimodaira | Speech Signal Analysis 2 | Hermansky (1990), PLP analysis of speech |
4 | Thu 22 January | 2 | Shimodaira | Acoustic 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 |
5 | Mon 26 January | 3 | Shimodaira | Acoustic modelling basics: HMMs and GMMs 2 | |
Mon 26 January | 3 | Renals | Tutorial / Group 1 | ||
Wed 28 January | 3 | Renals | Tutorial / Group 2 | ||
6 | Thu 29 January | 3 | Renals | Context-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 | 3 | Renals | Tutorial / Group 3 | ||
7 | Mon 2 February | 4 | Renals | Context-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 | 4 | Shimodaira | Introduction to Assignment 1 | Assignment 1: continuous speech recognition | |
Thu 5 February | 4 | Lab session (17:00) | |||
8 | Mon 9 February | 5 | Renals | Lexicon and language model (slides) |
J&M, Ch 4 Manning & Schutze, Ch 6 |
Mon 9 February | 5 | Lab session (17:00) | |||
Wed 11 February | 5 | Lab session (17:00) | |||
9 | Thu 12 February | 5 | Renals | Search and decoding (slides) | Aubert (2002) An overview of decoding techniques for large vocabulary continuous speech recognition |
Thu 12 February | 5 | Lab session (17:00) | |||
Mon 16 February | 6 | No Lecture - Innovative Learning Week | |||
Thu 19 February | 6 | No Lecture - Innovative Learning Week | |||
10 | Mon 23 February | 7 | Shimodaira | 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 | 7 | Lab session (17:30) | |||
Wed 25 February | 7 | Assignment 1 Deadline (16:00) | |||
11 | Thu 26 February | 7 | Renals | (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 |
12 | Mon 2 March | 8 | Renals | 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 | 8 | Renals | Tutorial / Group 1 | ||
Wed 4 March | 8 | Renals | Tutorial / Group 2 | ||
13 | Thu 5 March | 8 | Renals | Speaker adaptation 1 (slides) | G&Y review, sec. 5 Woodland (2001), Speaker adaptation for continuous density HMMs: A review |
Thu 5 March | 8 | Renals | Tutorial / Group 3 | ||
14 | Mon 9 March | 9 | Renals | Speaker adaptation 2 | |
Wed 11 March | 9 | Assignment 2 Deadline (16:00) | |||
15 | Thu 12 March | 9 | Peter Bell | Guest lecture: Transcribing TED talks (slides) | |
Mon 16 March | 10 | No lecture | |||
Thu 19 March | 10 | Renals | Wrap-up session |
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.
There are two pieces of coursework.
School of Informatics coursework policies:
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 |