Comparison of Self-Supervised Speech Pre-Training Methods on Flemish Dutch

by   Jakob Poncelet, et al.

Recent research in speech processing exhibits a growing interest in unsupervised and self-supervised representation learning from unlabelled data to alleviate the need for large amounts of annotated data. We investigate several popular pre-training methods and apply them to Flemish Dutch. We compare off-the-shelf English pre-trained models to models trained on an increasing amount of Flemish data. We find that the most important factors for positive transfer to downstream speech recognition tasks include a substantial amount of data and a matching pre-training domain. Ideally, we also finetune on an annotated subset in the target language. All pre-trained models improve linear phone separability in Flemish, but not all methods improve Automatic Speech Recognition. We experience superior performance with wav2vec 2.0 and we obtain a 30 XLSR-53 model on Flemish Dutch, after integration into an HMM-DNN acoustic model.


page 1

page 2

page 3

page 4


Measuring the Impact of Individual Domain Factors in Self-Supervised Pre-Training

Human speech data comprises a rich set of domain factors such as accent,...

Self-supervised Pre-training Reduces Label Permutation Instability of Speech Separation

Speech separation has been well-developed while there are still problems...

A Further Study of Unsupervised Pre-training for Transformer Based Speech Recognition

Building a good speech recognition system usually requires large amounts...

Pre-training strategies and datasets for facial representation learning

What is the best way to learn a universal face representation? Recent wo...

SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training

Unsupervised pre-training is now the predominant approach for both text ...

A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems

Self-supervised models for speech processing emerged recently as popular...

Unsupervised Pre-training of Bidirectional Speech Encoders via Masked Reconstruction

We propose an approach for pre-training speech representations via a mas...