ELEC-E5510 - Speech Recognition D, Lecture, 26.10.2022-9.12.2022

Topic outline

• Lectures
  In this list, the 2021 slides will be replaced by the 2022 ones after each lecture is given at latest. The titles may be identical, but the contents are improved each year based on feedback. The project works and their schedule changes each year. 

  For practicalities, e.g. regarding to the Lecture Quizzes and Exercises, check MyCourses > Course Practicalities
  

  • Select activity Lecture 1 - Feature extraction

    Lecture 1 - Feature extraction
    

  • Select activity features (2022) - final

    

    features (2022) - final File PDF

    • course organization
    • what is ASR
    • features of speech
    • MFCC
    • GMM
    • DNN
      
  • Select activity Lecture exercise 1: Gaussian mixture model

    

    Lecture exercise 1: Gaussian mixture model Assignment

    Completion

    Students must

    

    Make a submission

    Please upload your answer here, e.g. as a photo, text or pdf file
    

  • Select activity Lecture 2 - Phoneme modeling

    Lecture 2 - Phoneme modeling

  • Select activity HMM (2022) part1

    

    HMM (2022) part1 File PDF

    • Phonemes
    • HMMs
  • Select activity HMM (2022) part2

    

    HMM (2022) part2 File PDF
  • Select activity Lecture 2 HMM exercise

    

    Lecture 2 HMM exercise Assignment

    Completion

    Students must

    

    Make a submission
  • Select activity Lecture 3 - Language Modeling

    Lecture 3 - Language Modeling

  • Select activity LM (2022) part1

    

    LM (2022) part1 File PDF

    • lexicon
    • language modeling
    • n-grams, smoothing
  • Select activity Neural network language models (2022)

    

    Neural network language models (2022) File PDF

    • Intro to NNLM
    • Recurrent neural network language models
    • Long Short-Term Memory language models
    • Attention

    
    

  • Select activity Lecture 3 NNLM exercise

    

    Lecture 3 NNLM exercise Assignment

    Completion

    Students must

    

    Make a submission
  • Select activity Lecture 4 - Continuous speech and decoding

    Lecture 4 - Continuous speech and decoding
    

  • Select activity LVCSR (2022) - Final

    

    LVCSR (2022) - Final File PDF

    • recognition in continuous speech
    • token passing decoder
    • improving the recognition performance and speed
      
    • measuring the recognition performance
      
  • Select activity Lecture exercise 4: Token passing decoder

    Show more Show less

    Not available unless any of: You are a(n) Teacher ...

    Not available unless any of:

    • You are a(n) Teacher
    • You are a(n) Teacher (MC)
    • You are a(n) Student

    

    Lecture exercise 4: Token passing decoder Assignment

    Fill in the last column with final probabilities of the tokens, select the best token and output the corresponding state sequence!
    

    The goal is to verify that you have the learned the idea of the Token passing decoder. The extremely simplified HMM system is almost the same as in the 2B Viterbi algorithm exercise. The observed "sounds" are just quantified to either "A" or "B" with given probabilities in states S0 and S1.  Now the task is to find the most likely state sequence that can produce the sequence of sounds A, A, B using a simple language model (LM). The toy LM used here is a look-up table that tells probabilities for different state sequences, (0,1), (0,0,1) etc., up to 3-grams.
    

    Hint: You can either upload an edited source document, a pdf file, a photo of your notes or a text file with numbers. Whatever is easiest for you. To get the activity point the answer does not have to be correct.

    
    

  • Select activity Lecture 5 - End-to-end ASR with deep neural networ...

    Lecture 5 - End-to-end ASR with deep neural networks
    

    
    
  • Select activity Lecture 5 Slides

    

    Lecture 5 Slides File PDF
  • Select activity Lecture 5 exercise

    

    Lecture 5 exercise Assignment

    Completion

    Students must

    

    Make a submission
  • Select activity Lecture 5 slides (2022): About group works (Final)

    

    Lecture 5 slides (2022): About group works (Final) File PDF

    Preparation for the seminar sessions during the last two weeks

    Updated presentation schedule for the groups
    

  • Select activity Program for the last two weeks

    Program for the last two weeks
    

  • Select activity Wed 30 November: Presentations 1

    Wed 30 November: Presentations 1
    

  • Select activity Fri 2 December: Presentations 2 - 5

    Fri 2 December: Presentations 2 - 5
    

  • Select activity Wed 7 December: Presentations 6 - 9

    Wed 7 December: Presentations 6 - 9
    

  • Select activity Fri 9 December: Presentations 10 - 13

    Fri 9 December: Presentations 10 - 13
    

  • Select activity Text and media area

    
    

  • Select activity PresentersTwo days before (or earlier if possible)...

    Presenters
    

    • Two days before (or earlier if possible): Select one article for others to read and send the link to everybody in MyCourses discussion forum
    • One day before: Upload your slides in MyCourses. The latest version of slides will be published for others in MyCourses. You can also share a draft of the slides or a link in the discussion forum.
    • Practise to make sure that you will not exceed the 20 mins limit
    • Remember your “audience” duties for the other talks of your day

    Audience
    For each talk do this:
    

    • One day before: Read the provided articles and prepare one question to ask for each talk
    • Follow the talk and the slides and ask your question in chat
    • After the talk (max 1 day): Submit feedback (one for each talk) in MyCourses (all fields are required) to get activity points. The anonymous feedback (pros and cons) will be later shown to the presenters