Multilingual bottleneck features for subword modeling in zero-resource languages

TL;DR

This paper demonstrates that multilingual bottleneck features significantly improve subword modeling for zero-resource languages, especially when combined with unsupervised methods and high-quality same-word pairs.

Contribution

It shows that multilingual BNFs trained on multiple languages outperform unsupervised baselines and can be further enhanced with correspondence autoencoders.

Findings

BNFs trained on a single language outperform unsupervised baselines.

Including multiple languages in BNF training yields additional improvements.

cAE can further improve BNFs when high-quality same-word pairs are available.

Abstract

How can we effectively develop speech technology for languages where no transcribed data is available? Many existing approaches use no annotated resources at all, yet it makes sense to leverage information from large annotated corpora in other languages, for example in the form of multilingual bottleneck features (BNFs) obtained from a supervised speech recognition system. In this work, we evaluate the benefits of BNFs for subword modeling (feature extraction) in six unseen languages on a word discrimination task. First we establish a strong unsupervised baseline by combining two existing methods: vocal tract length normalisation (VTLN) and the correspondence autoencoder (cAE). We then show that BNFs trained on a single language already beat this baseline; including up to 10 languages results in additional improvements which cannot be matched by just adding more data from a single language. Finally, we show that the cAE can improve further on the BNFs if high-quality same-word pairs are available.