University Homepage School Homepage School Contacts School Search

ASR 2018-19  |  News Archive  |  Lectures  |  Labs  |  Coursework  |  Piazza

Automatic Speech Recognition (ASR) 2018-19: Labs

There will be weekly lab sessions using Kaldi to build speech recognition systems. Lab sessions will take place in AT-4.12 on

• Tuesdays 10:00-10:50
• Wednesdays 10:00-10:50
• Wednesdays 15:10-16:00

Select one lab session on Learn

• Lab 1 (Week 2): Data Preparation and Feature Extraction (Version 2.2 - last updated on 23/Jan.)
• Lab 2 (Week 3): Training monophone models
• Lab 3 (Week 4): Word recognition and triphone models
• Lab 4 (Week 5): Hybrid Acoustic Models [GPU version], [CPU version]
  No labs during Flexible Learning Week
• Drop-in lab (Week 6 - 26,27 Feb.)
• Lab 5 (Week 7 - 05,06 Mar.): Weighted finite-state transducers. NB: We use a Python notebook for this lab. Please run 'local/lab5_setup.sh' in your asrworkdir to start it.
• Drop-in lab (Week 8 - 12,13 Mar.)

---

Copyright (c) University of Edinburgh 2015-2019
The ASR course material is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License
licence.txt
This page maintained by Steve Renals.
Last updated: 2019/03/06 21:55:08UTC