Each module leads you through the material in a specific order: simply follow the tabs from left to right. But do also explore the entire course content on your own, look ahead to what is coming later, and browse the rest of this website including the forums.
This course operates a policy of continuous improvement. You will find some content is being revised for 2024-25. Don’t worry, it will be ready in time for you to study it. If you looked at previous versions of the course, the main difference is that we are introducing online quizzes through the semester rather than having one big exam at the end of semester. This was in response to the feedback that students didn’t get feedback, especially on the phon and signals component, until very late in semester. Also, hopefully spreading this out will relieve a bit of the exam/final paper stress that happens in early December.
Unlike last year, we won’t be having a separate Q&A slot as these were not particularly well attended last year. You should still feel free to ask questions during lectures, labs, and on the speech.zone forum!
The readings are specified in each module and are categorised as
- Essential (read all, aiming to complete within the week after the lecture on the module topic)
- Recommended (read if you have time, these readings will deepen your understanding but are not essential)
- Extra (only read if you’re interested or looking for extension material; some readings may be challenging; most are beyond the scope of the course)
- Thursday, 19 September 2024
-
-
Speech Processing Lecture 1: Introduction to Speech Processing / Speech ProductionThursday, 19 September 2024 at 09:00 - 11:007GS_F.21, 7 George SquareIn the first lecture, we'll give an overview of the course and then make a start on understanding the relationship between speech and text through articulatory phonetics.
Before this class: complete Module 1
Lecturer: Catherine Lai
-
- Monday, 23 September 2024
-
-
Speech Processing Milestone - enrolMonday, 23 September 2024Enrol for the course on EUCLID.
-
- Wednesday, 25 September 2024
-
-
Speech Processing Lab - Group 1Wednesday, 25 September 2024 at 09:00 - 10:50AT 4.02Praat basics and phonetics exercises . Before this lab: read Module 1 - Phonetics and Representations of Speech - Lab Staff: Catherine Lai, Atli Sigurgeirsson
-
Speech Processing Lab - Group 2Wednesday, 25 September 2024 at 16:10 - 18:00AT 4.02Praat basics and phonetics exercises Before this lab: read Module 1 - Phonetics and Representations of Speech - Lab Staff: Catherine Lai, Ariadna Sanchez, Atli Sigurgeirsson
-
- Thursday, 26 September 2024
-
-
Speech Processing Lecture 2: Acoustic phoneticsThursday, 26 September 2024 at 09:00 - 10:507GS_F.21, 7 George SquareBefore this class: watch module 2 videos and complete essential readings Lecturer: Catherine Lai
-
- Wednesday, 02 October 2024
-
-
Speech Processing Lab - Group 1Wednesday, 02 October 2024 at 09:00 - 10:50AT 4.02Acoustic phonetics, speech segmentation and variability Before this lab: go through Module 2 - Acoustics phonetics - Lab Staff: Catherine Lai, Atli Sigurgeirsson
-
Speech Processing Lab - Group 2Wednesday, 02 October 2024 at 16:10 - 18:00AT 4.02Acoustic phonetics, speech segmentation and variability Before this lab: go through Module 2 - Acoustics phonetics - Lab Staff: Catherine Lai, Ariadna Sanchez
-
- Thursday, 03 October 2024
-
-
Speech Processing Lecture 3: Digital Speech SignalsThursday, 03 October 2024 at 09:00 - 10:507GS_F.21, 7 George SquareWhat are spectrograms really? An introduction to Digital Signal Processing and the Discrete Fourier Transform
Before this class: complete Module 3
Lecturer: Catherine Lai
-
- Wednesday, 09 October 2024
-
-
Speech Processing Lab - Group 1Wednesday, 09 October 2024 at 09:00 - 10:50AT 4.02Interpreting the DFT and issues with digital signals (Jupyter Notebooks) Before this lab: read Module 3 - Digital Speech Signals - Lab Staff: Catherine Lai, Atli Sigurgeirsson
-
Speech Processing Lab - Group 2Wednesday, 09 October 2024 at 16:10 - 18:00AT 4.02Interpreting the DFT and issues with digital signals (Jupyter Notebooks) Before this lab: read Module 3 - Digital Speech Signals - Lab Staff: Catherine Lai, Atli Sigurgeirsson
-
- Thursday, 10 October 2024
-
-
Speech Processing Lecture 4: The Source-Filter ModelThursday, 10 October 2024 at 09:00 - 10:507GS_F.21, 7 George SquareBuilding on our understanding of the digital signal processing, we look at source-filter model from more of an engineering perspective
Before this class: complete Module 4
Lecturer: Catherine Lai
-
- Monday, 14 October 2024
-
-
Speech Processing Assessment - Phon/Signals online quiz (10% of course mark)Due on Wednesday, 16 October 2024 by 12:00Multiple choice questions: Test open for 2 days, but once you start you need to complete within 1 hour on Learn. This test covers modules 1-3.
-
- Tuesday, 15 October 2024
-
-
Speech Processing Assessment - Phon/Signals online quiz (10% of course mark)Due on Wednesday, 16 October 2024 by 12:00Multiple choice questions: Test open for 2 days, but once you start you need to complete within 1 hour on Learn. This test covers modules 1-3.
-
- Wednesday, 16 October 2024
-
-
Speech Processing Lab - Group 1Wednesday, 16 October 2024 at 09:00 - 10:50AT 4.02Exploring the source-filter model (Jupyter notebooks). Before this lab: read Module 4 - the Source-Filter Model - Lab Staff: Catherine Lai, Ariadna Sanchez (If there is time left over, you can start playing with Festival.)
-
Speech Processing Assessment - Phon/Signals online quiz (10% of course mark)Due on Wednesday, 16 October 2024 by 12:00Multiple choice questions: Test open for 2 days, but once you start you need to complete within 1 hour on Learn. This test covers modules 1-3.
-
Speech Processing Lab - Group 2Wednesday, 16 October 2024 at 16:10 - 18:00AT 4.02Exploring the source-filter model (Jupyter notebooks). Before this lab: read Module 4 - the Source-Filter Model - Lab Staff: Catherine Lai, Ariadna Sanchez (If there is time left over, you can start playing with Festival.)
-
- Thursday, 17 October 2024
-
-
Speech Processing Lecture 5: Speech Synthesis - Phonemes and the Front-EndThursday, 17 October 2024 at 09:00 - 10:507GS_F.21, 7 George SquarePronunciation, including letter-to-sound models, and predicting prosody. All these tasks can be done with Classification And Regression Trees (CARTs).
Before this class: complete Module 5
Lecturer: Catherine Lai
-
- Friday, 18 October 2024
-
-
Speech Processing Milestone - assignment 1Friday, 18 October 2024Prepare for the first assignment by reading through the complete instructions on speech.zone. Start work on the assignment, using the forums to get any technical help you need.
-
- Wednesday, 23 October 2024
-
-
Speech Processing Lab - Group 1Wednesday, 23 October 2024 at 09:00 - 10:50AT 4.02Start TTS assignment Before this lab: read Module 5 - speech synthesis – phonemes and the front end - Lab Work through the practical exercises “Getting Started” and “Step-by-step” in the assignment specification https://speech.zone/exercises/the-festival-text-to-speech-system/ Staff: Simon King, Atli Sigurgeirsson, Opeyemi Okasuade
-
Speech Processing Lab - Group 2Wednesday, 23 October 2024 at 16:10 - 18:00AT 4.02Start TTS assignment
Before this lab: read Module 5 - speech synthesis – phonemes and the front end - Lab
Work through the practical exercises “Getting Started” and “Step-by-step” in the assignment specification https://speech.zone/exercises/the-festival-text-to-speech-system/
Staff: Simon King, Ariadna Sanchez, Opeyemi Osakuade
-
- Thursday, 24 October 2024
-
-
Speech Processing Lecture 6: Speech Synthesis - Waveform GenerationThursday, 24 October 2024 at 09:00 - 10:507GS_F.21, 7 George SquareManipulating recorded speech signals to create new utterances.
Before this class: complete Module 6
Lecturer: Catherine Lai
-
- Friday, 25 October 2024
-
-
Speech Processing Milestone - assignment 1Friday, 25 October 2024Work through the practical exercises "Getting Started" and "Step-by-step". Perform "Step-by-step" synthesis for at least 2 different sentences. Construct sentences that are short but contain plenty of ambiguity that needs resolving, so that as many of the steps as possible in Festival's front end actually do something interesting. Find at least one example where the ambiguity was correctly resolved, and one where it was not.
-
- Monday, 28 October 2024
-
-
Speech Processing Assessment - TTS/Signals online quiz (10% of course mark)Due on Wednesday, 30 October 2024 by 12:00Multiple choice questions: Test open for 2 days, but once you start you need to complete within 1 hour on Learn. This test will cover material from modules 4-6.
-
- Tuesday, 29 October 2024
-
-
Speech Processing Assessment - TTS/Signals online quiz (10% of course mark)Due on Wednesday, 30 October 2024 by 12:00Multiple choice questions: Test open for 2 days, but once you start you need to complete within 1 hour on Learn. This test will cover material from modules 4-6.
-
- Wednesday, 30 October 2024
-
-
Speech Processing Milestone - assignment 1Wednesday, 30 October 2024Find multiple errors in each of the categories required for the assignment.
-
Speech Processing Lab - Group 1Wednesday, 30 October 2024 at 09:00 - 10:50AT 4.02Continue TTS assignment Before this lab: read Module 6 - Speech Synthesis – waveform generation and connected speech Lab, and bring a writing sample with you to the lab Staff: Simon King, Atli Sigurgeirsson, Opeyemi Okasuade
-
Speech Processing Assessment - TTS/Signals online quiz (10% of course mark)Due on Wednesday, 30 October 2024 by 12:00Multiple choice questions: Test open for 2 days, but once you start you need to complete within 1 hour on Learn. This test will cover material from modules 4-6.
-
Speech Processing Lab - Group 2Wednesday, 30 October 2024 at 16:10 - 18:00AT 4.02Continue TTS assignment Before this lab: read Module 6 - Speech Synthesis – waveform generation and connected speech Lab, and bring a writing sample with you to the lab Staff: Simon King, Ariadna Sanchez, Opeyemi Osakuade
-
- Thursday, 31 October 2024
-
-
Speech Processing - No lecture this weekThursday, 31 October 2024 at 09:00 - 10:50
-
- Friday, 01 November 2024
-
-
Speech Processing Milestone - assignment 1Friday, 01 November 2024Decide which 1-2 errors in each category you will include in your report. Draft a good explanation of each of them. Assemble the evidence you need to present in the report, such as incorrect/correct pronunciations, annotated spectrograms, etc. Be sure to follow the report structure explain in the assignment instructions.
-
- Monday, 04 November 2024
-
-
Speech Processing Assessment - submit assignment 1 (30% of course mark)Due on Monday, 04 November 2024 by 12:00via Learn
-
- Wednesday, 06 November 2024
-
-
Speech Processing Lab - Group 1Wednesday, 06 November 2024 at 09:00 - 10:50AT 4.02Command line and shell scripting
Before this lab: Work through the material in the Intermission module then come to the lab to get help.
Staff: Atli Sigurgeirsson, Simon King -
Speech Processing Lab - Group 2Wednesday, 06 November 2024 at 16:10 - 18:00AT 4.02Command line and shell scripting
Before this lab: Work through the material in the Intermission module then come to the lab to get help.
Staff: Simon King, Ariadna Sanchez
-
- Thursday, 07 November 2024
-
-
Speech Processing Lecture 7: Speech Recognition - Pattern RecognitionThursday, 07 November 2024 at 09:00 - 10:507GS_F.21, 7 George SquareWe now start on an introduction to Automatic Speech Recognition, starting with the concept of pattern recognition.
Before this class: complete Module 7
Lecturer: Catherine Lai
-
- Monday, 11 November 2024
-
-
Speech Processing Milestone - assignment 2Monday, 11 November 2024Read through assignment 2 instructions and make sure you have a basic understanding of the linux command line by going through the LinkedIn online course from last week: https://www.linkedin.com/learning/learning-linux-command-line-2/?u%3D50251009%26auth%3Dtrue&sa=D&source=calendar&usd=2&usg=AOvVaw3E6yRZAbRovSbOoP8-Wj0c" target="_blank">https://www.linkedin.com/learning/learning-linux-command-line-2/?u=50251009&auth=true
-
- Wednesday, 13 November 2024
-
-
Speech Processing Milestone - assignment 2Wednesday, 13 November 2024Run the scripts given in the assignment to train a digit recogniser using data from a single user (e.g., simonk) by hand-coding that username into each script. Run the 4 scripts and obtain a WER for that user (for simonk you should get 0% WER). Try testing that recogniser on data from another user.
-
Speech Processing Lab - Group 1Wednesday, 13 November 2024 at 09:00 - 10:50AT 4.02Start ASR assignment Before this lab: read Module 7 - Speech Recognition – Pattern matching - Lab Staff: Simon King, Atli Sigurgeirsson
-
Speech Processing Lab - Group 2Wednesday, 13 November 2024 at 16:10 - 18:00AT 4.02Start ASR assignment Before this lab: read Module 7 - Speech Recognition – Pattern matching Lab Staff: Simon King, Ariadna Sanchez
-
- Thursday, 14 November 2024
-
-
Speech Processing Lecture 8: Speech Recognition - Feature EngineeringThursday, 14 November 2024 at 09:00 - 10:507GS_F.21, 7 George SquareTo get the best out of machine learning, we can prepare features that reflect our knowledge of the problem, and suit our chosen model.
Before this class: complete Module 8
Lecturer: Catherine Lai
-
- Friday, 15 November 2024
-
-
Speech Processing Milestone - assignment 2Friday, 15 November 2024Improve the scripts so that they accept the user's name as a command line argument. Combine initialise_models and train_models into a single script called initialise_and_train_models (alternatively, initialise_and_train_models can run initialise_models then train_models). Modify recognise_test_data so that it first deletes any files left in the rec directory by a previous experiment.
-
- Wednesday, 20 November 2024
-
-
Speech Processing Milestone - assignment 2Wednesday, 20 November 2024Write a script called run_experiment that takes two command line arguments: the first is the name of a file containing the users in the training set, and the other is for the test set. The script should train, test and score a complete ASR system, by running initialise_and_train_models, then recognise_test_data, then results. It will print out the WER at the end. Use the forums to learn all the shell scripting techniques needed and keep asking questions whenever you get stuck. Design your first few experiments.
-
Speech Processing Lab - Group 1Wednesday, 20 November 2024 at 09:00 - 10:50AT 4.02Continue ASR assignment Before this lab: continue working in your own time on the assignment so that you have questions ready to ask in the lab Staff: Simon King, Atli Sigurgeirsson
-
Speech Processing Lab - Group 2Wednesday, 20 November 2024 at 16:10 - 18:00AT 4.02Continue ASR assignment Before this lab: continue working in your own time on the assignment so that you have questions ready to ask in the lab Staff: Simon King, Ariadna Sanchez
-
- Thursday, 21 November 2024
-
-
Speech Processing Lecture 9: Speech Recognition - the Hidden Markov ModelThursday, 21 November 2024 at 09:00 - 10:507GS_F.21, 7 George SquareWe now replace pattern matching with a generative model that is learned from data.
Before this class: complete Module 9
Lecturer: Catherine Lai
-
- Friday, 22 November 2024
-
-
Speech Processing Milestone - assignment 2Friday, 22 November 2024Create all the training and test sets required for your experiments. Run all your isolated digits experiments. Start drafting your report, ready for the writing clinics next week.
-
- Monday, 25 November 2024
-
-
Speech Processing Assessment - ASR online quiz (10% of course mark)Due on Wednesday, 27 November 2024 by 12:00Multiple choice questions: Test open for 2 days, but once you start you need to complete within 1 hour on Learn. This test will cover material from modules 7-9.
-
- Tuesday, 26 November 2024
-
-
Speech Processing Assessment - ASR online quiz (10% of course mark)Due on Wednesday, 27 November 2024 by 12:00Multiple choice questions: Test open for 2 days, but once you start you need to complete within 1 hour on Learn. This test will cover material from modules 7-9.
-
- Wednesday, 27 November 2024
-
-
Speech Processing Milestone - assignment 2Wednesday, 27 November 2024Decide which aspect of your writing you need most help so you can ask for help from the PPLS skills centre or in the labs
-
Speech Processing Lab - Group 1Wednesday, 27 November 2024 at 09:00 - 10:50AT 4.02Complete ASR assignment Before this lab: continue working in your own time on the assignment so that you have questions ready to ask in the lab Staff: Simon King, Atli Sigurgeirsson
-
Speech Processing Assessment - ASR online quiz (10% of course mark)Due on Wednesday, 27 November 2024 by 12:00Multiple choice questions: Test open for 2 days, but once you start you need to complete within 1 hour on Learn. This test will cover material from modules 7-9.
-
Speech Processing Lab - Group 2Wednesday, 27 November 2024 at 16:10 - 18:00AT 4.02Complete ASR assignment Before this lab: continue working in your own time on the assignment so that you have questions ready to ask in the lab Staff: Simon King, Ariadna Sanchez
-
- Thursday, 28 November 2024
-
-
Speech Processing Lecture 10: Speech Recognition - Connected speech & HMM trainingThursday, 28 November 2024 at 09:00 - 10:507GS_F.21, 7 George SquareHMMs extend easily to connected speech so finally we put everything together to make a complete speech recognition system. We'll also learn how to train an HMM from data.
Before this class: complete Module 10
Lecturer: Catherine Lai
-
- Friday, 29 November 2024
-
-
Speech Processing Milestone - assignment 2Friday, 29 November 2024Finalise all the results tables and plots for your report, apart from digit sequences.
-
- Monday, 02 December 2024
-
-
Speech Processing Milestone - assignment 2Monday, 02 December 2024If you've completed the rest of the assignment, create a language model for digit sequences. The techniques for this will have been taught in Module 10. Start building a system for digit sequences.
-
- Tuesday, 03 December 2024
-
-
Speech Processing Milestone - assignment 2Tuesday, 03 December 2024Finish the system for digit sequences. Finalise your report, reading for final proof-reading and one last editing pass.
-
- Wednesday, 04 December 2024
-
-
Speech Processing Lab - Groups 1 & 2Wednesday, 04 December 2024 at 09:00 - 10:50AT 4.02Last chance for help with the ASR assignment Both groups welcome (priority to Group 1 if the lab is full) Staff: Simon King, Atli Sigurgeirsson
-
Speech Processing Lab - Groups 2 & 1Wednesday, 04 December 2024 at 16:10 - 18:00AT 4.02Last chance for help with the ASR assignment Both groups welcome (priority to Group 2 if the lab is full) Staff: Simon King
-
- Thursday, 05 December 2024
-
-
Speech Processing Speech Processing Assessment - submit assignment 2 (40% of course mark) - date subject to confirmationDue on Thursday, 05 December 2024 by 12:00via Learn
-