University Homepage School Homepage School Contacts School Search

ASR 2021-22  |  News Archive  |  Lectures  |  Labs  |  Coursework  |  Piazza

Automatic Speech Recognition (ASR) 2021-22: Labs

There will be weekly lab sessions using OpenFst and Python to build speech recognition systems. Lab sessions will start in Week 3, and will run in-person in Appleton Tower. You should already have been allocated to a lab session.

• Lab 01: Tuesdays 13.10, 6.06 AT (demonstator Zeyu Zhao)
• Lab 02: Wednesdays 10.00, 6.06 AT (demonstrator Jie Chi)
• Lab 02: Wednesdays 13.10, 5.05-West Lab AT (demonstrator Ramon Sanabria)
• Lab 03: Fridays 13.10, 5.05- West Lab AT (demonstrator Electra Wallington)

Labs are available via a GitHub repository. Details of the setup can be found on a pinned Piazza post. Labs 1-5 are worth 10% of the total mark for the course. Submissions are due at 9am Monday mornings in the second week following the labs – details on Learn. Following the first five labs, there are three optional labs teaching the Kaldi ASR toolkit.

An introduction to the labs is presented in Lecture 5 (slides).

Compulsory labs (via GitHub)

• Lab 1 (Week 3): Building HMMs with OpenFst
• Lab 2 (Week 4): Computing HMM probabilities
• Lab 3 (Week 5): Viterbi decoding (1)
• Lab 4 (Week 6): Viterbi decoding (2)
• Lab 5 (Week 7): WFST operations

Optional Kaldi labs (PDFs)

• Lab 6 (Week 8): Kaldi: data preparation and feature extraction
• Lab 7 (Week 9): Kaldi: training monophone models
• Lab 8 (Week 10): Kaldi: training triphone models

---

Copyright (c) University of Edinburgh 2015-2022
The ASR course material is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License
licence.txt
This page maintained by Peter Bell.
Last updated: 2022/03/28 15:43:40UTC