Towards Zero-shot Learning for Automatic Phonemic Transcription

by   Xinjian Li, et al.

Automatic phonemic transcription tools are useful for low-resource language documentation. However, due to the lack of training sets, only a tiny fraction of languages have phonemic transcription tools. Fortunately, multilingual acoustic modeling provides a solution given limited audio training data. A more challenging problem is to build phonemic transcribers for languages with zero training data. The difficulty of this task is that phoneme inventories often differ between the training languages and the target language, making it infeasible to recognize unseen phonemes. In this work, we address this problem by adopting the idea of zero-shot learning. Our model is able to recognize unseen phonemes in the target language without any training data. In our model, we decompose phonemes into corresponding articulatory attributes such as vowel and consonant. Instead of predicting phonemes directly, we first predict distributions over articulatory attributes, and then compute phoneme distributions with a customized acoustic model. We evaluate our model by training it using 13 languages and testing it using 7 unseen languages. We find that it achieves 7.7 multilingual model.


page 1

page 2

page 3

page 4


AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages

Pretrained multilingual models are able to perform cross-lingual transfe...

How Phonotactics Affect Multilingual and Zero-shot ASR Performance

The idea of combining multiple languages' recordings to train a single a...

Zero-shot Learning with Complementary Attributes

Zero-shot learning (ZSL) aims to recognize unseen objects using disjoint...

Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual Transferability

Pretrained multilingual models enable zero-shot learning even for unseen...

Discovering Phonetic Inventories with Crosslingual Automatic Speech Recognition

The high cost of data acquisition makes Automatic Speech Recognition (AS...

Few-Shot Unlearning by Model Inversion

We consider the problem of machine unlearning to erase a target dataset,...

Tinkering Under the Hood: Interactive Zero-Shot Learning with Net Surgery

We consider the task of visual net surgery, in which a CNN can be reconf...