Unsupervised Word Segmentation from Speech with Attention

Pierre Godard, Marcely Zanon-Boito, Lucas Ondel, Alexandre Berard, François Yvon, Aline Villavicencio, Laurent Besacier

We present a first attempt to perform attentional word segmentation directly from the speech signal, with the final goal to automatically identify lexical units in a low-resource, unwritten language (UL). Our methodology assumes a pairing between recordings in the UL with translations in a well-resourced language. It uses Acoustic Unit Discovery (AUD) to convert speech into a sequence of pseudo-phones that is segmented using neural soft-alignments produced by a neural machine translation model. Evaluation uses an actual Bantu UL, Mboshi; comparisons to monolingual and bilingual baselines illustrate the potential of attentional word segmentation for language documentation.

Knowledge Graph

arrow_drop_up

Comments

Sign up or login to leave a comment