Översikt

  • Uppgifter

    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

    • Fil icon
      Lectures 1-2 slides (2023) Fil PDF
      • course organization
      • what is ASR
      • features of speech
      • MFCC
      • GMM
      • DNN
    • Inlämningsuppgift icon
      Lecture 1-2 exercise: Gaussian mixture model Inlämningsuppgift

      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

    • Fil icon
      Lecture 3-4 slides (2023) Fil PDF
      • Phonemes
      • HMMs
    • Inlämningsuppgift icon
      Lecture 3: exercise Forward Inlämningsuppgift

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

    • Inlämningsuppgift icon
      Lecture 3: exercise Viterbi Inlämningsuppgift

      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

    • Fil icon
      Lecture 5 slides (2023): N-gram language models Fil PDF
      • lexicon
      • language modeling
      • n-grams, smoothing
    • Fil icon
      Lecture 6 slides (2023): Neural network language models Fil PDF

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


    • Inlämningsuppgift icon
      Lecture 6 NNLM exercise Inlämningsuppgift

      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

    • Fil icon
      Lecture 7-8 slides (2023) Fil PDF
      • recognition in continuous speech
      • token passing decoder
      • improving the recognition performance and speed
      • measuring the recognition performance
    • Inlämningsuppgift icon
      Lecture 7 exercise: Token passing decoder Inlämningsuppgift

      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


    • Tillgänglig om: Du tillhör någon grupp
      Fil icon
      Lecture 9 slides (2023) Fil PDF
    • Tillgänglig om: Du tillhör någon grupp
      Fil icon
      Lecture 10 slides (2023) Fil PDF
    • Tillgänglig om: Du tillhör någon grupp
      Fil icon
      Lecture 9-10 slides (2022) Fil PDF

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

    • Inlämningsuppgift icon
      Lecture 9 exercise Inlämningsuppgift
    • Fil icon
      Presentations for the weeks 6-7 Fil PDF

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

◄ Previous section
Course Practicalities
Next section ►
Assignments