Unsupervised Word Discovery: Boundary Detection with Clustering vs. Dynamic Programming

2024-09-22 · Simon Malan, Benjamin van Niekerk, Herman Kamper

We look at the long-standing problem of segmenting unlabeled speech into word-like segments and clustering these into a lexicon. Several previous methods use a scoring model coupled with dynamic programming to find an optimal segmentation. Here we propose a much simpler strategy: we predict word boundaries using the dissimilarity between adjacent self-supervised features, then we cluster the predicted segments to construct a lexicon. For a fair comparison, we update the older ES-KMeans dynamic programming method with better features and boundary constraints. On the five-language ZeroSpeech benchmarks, our simple approach gives similar state-of-the-art results compared to the new ES-KMeans+ method, while being almost five times faster. Project webpage: https://s-malan.github.io/prom-seg-clus.

📄 PDF Abstract BibTeX arXiv:2409.14486

Code (0)

등록된 구현이 없습니다.

Tasks

Boundary DetectionClustering

Should Top-Down Clustering Affect Boundaries in Unsupervised Word Discovery?

2025-07-25 · Simon Malan, Benjamin van Niekerk, Herman Kamper arxiv

We investigate the problem of segmenting unlabeled speech into word-like units and clustering these to create a lexicon. Prior work can be categorized into two frameworks. Bottom-up methods first determine boundaries and…

Unsupervised Spoken Term Discovery Based on Re-clustering of Hypothesized Speech Segments with Siamese and Triplet Networks

2020-11-28 · Man-Ling Sung, Tan Lee

Spoken term discovery from untranscribed speech audio could be achieved via a two-stage process. In the first stage, the unlabelled speech is decoded into a sequence of subword units that are learned and modelled in an u…

Clustering Triplet

KULCQ: An Unsupervised Keyword-based Utterance Level Clustering Quality Metric

2024-11-15 · Pranav Guruprasad, Negar Mokhberian, Nikhil Varghese, Chandra Khatri 외

Intent discovery is crucial for both building new conversational agents and improving existing ones. While several approaches have been proposed for intent discovery, most rely on clustering to group similar utterances t…

Clustering Intent Discovery

Discovery Team at SemEval-2020 Task 1: Context-sensitive Embeddings Not Always Better than Static for Semantic Change Detection

2020-12-01 · SEMEVAL 2020 · Matej Martinc, Syrielle Montariol, Elaine Zosa, Lidia Pivovarova

This paper describes the approaches used by the Discovery Team to solve SemEval-2020 Task 1 - Unsupervised Lexical Semantic Change Detection. The proposed method is based on clustering of BERT contextual embeddings, foll…

Change Detection Clustering

Recovering the Zipfian Distribution in Unsupervised Term Discovery

2026-06-09 · Danel Slabbert, Simon Malan, Herman Kamper arxiv

Unsupervised term discovery involves segmenting unlabelled speech into word- or syllable-like units and clustering these into a lexicon of candidate types. True lexicons follow a Zipfian distribution, yet the dominant ce…

Graph Clustering