Skip to content
Multilingual acoustic word embedding approaches applied and evaluated on GlobalPhone data.
Jupyter Notebook Python Other
Branch: master
Clone or download

Latest commit

Fetching latest commit…
Cannot retrieve the latest commit at this time.

Files

Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
blackbox
data
downsample
embeddings Added utility script Mar 30, 2020
features
notebooks
qbe
samediff
src
.gitignore
Makefile
install_local.sh
paths.py
readme.md

readme.md

Multilingual Acoustic Word Embeddings on GlobalPhone

Overview

Multilingual acoustic word embedding approaches are implemented and evaluated on the GlobalPhone corpus. The experiments are described in:

  • H. Kamper, Y. Matusevych, and S.J. Goldwater "Multilingual acoustic word embedding models for processing zero-resource languages," in Proc. ICASSP, 2020. [arXiv]

Please cite this paper if you use the code.

Disclaimer

The code provided here is not pretty. But I believe that research should be reproducible. I provide no guarantees with the code, but please let me know if you have any problems, find bugs or have general comments.

Download datasets

The GlobalPhone corpus and forced alignments of the data needs to be obtained. GlobalPhone needs to be paid for. If you have proof of payment, we can give you access to the forced alignments. Save the data and forced alignments in a separate directory and update the paths.py file to point to the data directories.

Install dependencies

You will require the following:

To install speech_dtw (required for same-different evaluation) and shorten (required for processing audio), run ./install_local.sh.

Extract speech features

Update the paths in paths.py to point to the data directories. If you are using docker, paths.py will already point to the mounted directories. Extract MFCC features in the features/ directory as follows:

cd features
./extract_features.py SP

You need to run extract_features.py for all languages; run it without any arguments to see all 16 language codes.

Evaluate frame-level features using the same-different task

This is optional. To perform frame-level same-different evaluation based on dynamic time warping (DTW), follow samediff/readme.md.

Obtain downsampled acoustic word embeddings

Extract and evaluate downsampled acoustic word embeddings by running the steps in downsample/readme.md.

Train neural acoustic word embeddings

Train and evaluate neural network acoustic word embedding models by running the steps in embeddings/readme.md.

Analyse embedding models

Analyse different properties/aspects of the acoustic word embedding models by running the steps in blackbox/readme.md.

Query-by-example search

Perform query-by-example search experiments by running the steps in qbe/readme.md.

Unit tests

In the root project directory, run make test to run unit tests.

References

Contributors

License

The code is distributed under the Creative Commons Attribution-ShareAlike license (CC BY-SA 4.0).

You can’t perform that action at this time.