Unsupervised Word Segmentation using K Nearest Neighbors [article]

Tzeviya Sylvia Fuchs, Yedid Hoshen, Joseph Keshet
2022 arXiv   pre-print
In this paper, we propose an unsupervised kNN-based approach for word segmentation in speech utterances. Our method relies on self-supervised pre-trained speech representations, and compares each audio segment of a given utterance to its K nearest neighbors within the training set. Our main assumption is that a segment containing more than one word would occur less often than a segment containing a single word. Our method does not require phoneme discovery and is able to operate directly on
more » ... trained audio representations. This is in contrast to current methods that use a two-stage approach; first detecting the phonemes in the utterance and then detecting word-boundaries according to statistics calculated on phoneme patterns. Experiments on two datasets demonstrate improved results over previous single-stage methods and competitive results on state-of-the-art two-stage methods.
arXiv:2204.13094v1 fatcat:tqv2n5gubnf3hp4oibgyjrox2u