Multilingual Acoustic Word Embedding Models for Processing Zero-Resource Languages

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in “zero-resource” speech search, indexing and discovery systems. Here we propose to train a single supervised embedding model on labelled data from multiple well-resourced languages and then apply it to unseen zeroresource languages. For this transfer learning approach, we consider two multilingual recurrent neural network models: a discriminative classifier trained on the joint vocabularies of all training languages, and a correspondence autoencoder trained to reconstruct word pairs. We test these using a word discrimination task on six target zero-resource languages. When trained on seven well-resourced languages, both models perform similarly and outperform unsupervised models trained on the zero-resource languages. With just a single training language, the second model works better, but performance depends more on the particular training–testing language pair.
Original languageEnglish
Title of host publication ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages6414-6418
Number of pages5
ISBN (Electronic)978-1-5090-6631-5
ISBN (Print)978-1-5090-6632-2
DOIs
Publication statusPublished - 14 May 2020
Event2020 IEEE International Conference on Acoustics, Speech, and Signal Processing - Barcelona, Spain
Duration: 4 May 20208 May 2020
Conference number: 45

Publication series

Name
PublisherIEEE
ISSN (Print)1520-6149
ISSN (Electronic)2379-190X

Conference

Conference2020 IEEE International Conference on Acoustics, Speech, and Signal Processing
Abbreviated titleICASSP 2020
CountrySpain
CityBarcelona
Period4/05/208/05/20

Keywords

  • Acoustic word embedding
  • multilingual models
  • Zero-resource speech processing
  • query-by-example

Fingerprint Dive into the research topics of 'Multilingual Acoustic Word Embedding Models for Processing Zero-Resource Languages'. Together they form a unique fingerprint.

Cite this