Multilingual bottleneck features for subword modeling in zero-resource languages

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.

arXiv comment5 pages, 2 figures, 4 tables; accepted at Interspeech 2018

Cited by in corpus (6)

• Few-Shot Keyword Spotting in Any Language
• Feature learning for efficient ASR-free keyword spotting in low-resource languages
• Unsupervised feature learning for speech using correspondence and Siamese networks
• Multilingual Bottleneck Features for Improving ASR Performance of Code-Switched Speech in Under-Resourced Languages
• Towards Zero-shot Learning for Automatic Phonemic Transcription
• Multilingual and crosslingual speech recognition using phonological-vector based phone embeddings