Simple and Effective Zero-shot Cross-lingual Phoneme Recognition
TL
TL;DR
This paper extends previous work on zero-shot cross-lingual transfer learning by fine-tuning a multilingually pretrained wav2vec 2.0 model to transcribe unseen languages by mapping phonemes of the training languages to the target language using articulatory features.
Abstract
Recent progress in self-training, self-supervised pretraining and unsupervised learning enabled well performing speech recognition systems without any labeled data. However, in many cases there is labeled data available for related languages which is not utilized by these methods. This paper extends previous work on zero-shot cross-lingual transfer learning by fine-tuning a multilingually pretrained wav2vec 2.0 model to transcribe unseen languages. This is done by mapping phonemes of the training languages to the target language using articulatory features. Experiments show that this simple method significantly outperforms prior work which introduced task-specific architectures and used only part of a monolingually pretrained model.
References39 items
1
Discovering Phonetic Inventories with Crosslingual Automatic Speech Recognition
2
Zero-Shot Cross-Lingual Phonetic Recognition with External Language Embedding
3
Differentiable Allophone Graphs for Language-Universal Speech Recognition
4
Multilingual transfer of acoustic word embeddings improves when training on languages related to the target zero-resource language
5