Voice Conversion Based Speaker Normalization for Acoustic Unit Discovery
Abstract
Discovering speaker independent acoustic units purely from spoken input is known to be a hard problem. In this work we propose an unsupervised speaker normalization technique prior to unit discovery. It is based on separating speaker related from content induced variations in a speech signal with an adversarial contrastive predictive coding approach. This technique does neither require transcribed speech nor speaker labels, and, furthermore, can be trained in a multilingual fashion, thus achieving speaker normalization even if only few unlabeled data is available from the target language. The speaker normalization is done by mapping all utterances to a medoid style which is representative for the whole database. We demonstrate the effectiveness of the approach by conducting acoustic unit discovery with a hidden Markov model variational autoencoder noting, however, that the proposed speaker normalization can serve as a front end to any unit discovery system. Experiments on English, Yoruba and Mboshi show improvements compared to using non-normalized input.
Cite
@article{arxiv.2105.01786,
title = {Voice Conversion Based Speaker Normalization for Acoustic Unit Discovery},
author = {Thomas Glarner and Janek Ebbers and Reinhold Häb-Umbach},
journal= {arXiv preprint arXiv:2105.01786},
year = {2021}
}
Comments
Submitted to Interspeech 2021