# Unsupervised Word Segmentation using K Nearest Neighbors

arXiv: https://arxiv.org/abs/2204.13094 · HTML: https://mlsanity.com/paper/2204.13094/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2022.

## Built on by (most cited first, 5 of 5)

- [End-to-End Simultaneous Speech Translation with Differentiable Segmentation](https://mlsanity.com/paper/2305.16093/) (2023)
- [Unsupervised Word Segmentation Using Temporal Gradient Pseudo-Labels](https://mlsanity.com/paper/2304.00993/) (2023)
- [Unified Segment-to-Segment Framework for Simultaneous Sequence Generation](https://mlsanity.com/paper/2310.17940/) (2023)
- [Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentences](https://mlsanity.com/paper/2303.08809/) (2023)
- [Leveraging multilingual transfer for unsupervised semantic acoustic word embeddings](https://mlsanity.com/paper/2307.02083/) (2023)

## Abstract (arXiv)

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 pre-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.