Osion kuvaus

  • In this list, the 2022 slides will be replaced by the 2023 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

    • Lectures 1-2 Feature extraction and modeling

    • Tiedosto icon
      • course organization
      • what is ASR
      • features of speech
      • MFCC
      • GMM
      • DNN
    • Tehtävä icon
      Lecture 1-2 exercise: Gaussian mixture model Tehtävä

      Instructions can be found in the pdf file. Please upload your answer here, e.g. as a photo, text or pdf file

    • Lectures 3-4 - Phoneme modeling

    • Tehtävä icon
      Lecture 3: exercise Forward Tehtävä

      Please type or upload your calculations here, e.g. as a photo, text or pdf file to earn a lecture activity point.

    • Tehtävä icon
      Lecture 3: exercise Viterbi Tehtävä

      Please type or upload your calculations here, e.g. as a photo, text or pdf file to earn a lecture activity point.

    • Lectures 5-6 - Language Modeling

    • Tiedosto icon
      • lexicon
      • language modeling
      • n-grams, smoothing
    • Tiedosto icon

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


    • Tehtävä icon
      Lecture 6 NNLM exercise Tehtävä

      Please type or upload your calculations here, e.g. as a photo, text or pdf file to earn a lecture activity point.

    • Lectures 7-8 - Continuous speech and decoding

    • Tiedosto icon
      • recognition in continuous speech
      • token passing decoder
      • improving the recognition performance and speed
      • measuring the recognition performance
    • Tehtävä icon
      Lecture 7 exercise: Token passing decoder Tehtävä

      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.


    • Lecture 9-10 - End-to-end ASR with deep neural networks


    • Saatavilla vasta, kun: Kuulut mihin tahansa ryhmään
      Tiedosto icon
      Lecture 9 slides (2023) Tiedosto PDF
    • Saatavilla vasta, kun: Kuulut mihin tahansa ryhmään
      Tiedosto icon
      Lecture 10 slides (2023) Tiedosto PDF
    • Saatavilla vasta, kun: Kuulut mihin tahansa ryhmään
      Tiedosto icon
      Lecture 9-10 slides (2022) Tiedosto PDF

      This is 2022, but because the content was quite different (focusing on attention-based encoder-decoder architectures) this maybe worth studying, too.

    • Tehtävä icon
      Lecture 9 exercise Tehtävä
    • Tiedosto icon

      Here's the presentation schedule as finalized at the last lecture.