A K-nearest neighbours approach to unsupervised spoken term discovery

Alexis Thual (1, 2) , Corentin Dancette (2, 1) , Julien Karadayi (1, 2) , Juan Benjumea (1, 2) , Emmanuel Dupoux (2, 1)

1 CoML - Apprentissage machine et développement cognitif
2 LSCP - Laboratoire de sciences cognitives et psycholinguistique

Unsupervised spoken term discovery is the task of finding recurrent acoustic patterns in speech without any annotations. Current approaches consists of two steps: (1) discovering similar patterns in speech, and (2) partitioning those pairs of acoustic tokens using graph clustering methods. We propose a new approach for the first step. Previous systems used various approximation algorithms to make the search tractable on large amounts of data. Our approach is based on an optimized k-nearest neighbours (KNN) search coupled with a fixed word embedding algorithm. The results show that the KNN algorithm is robust across languages, consistently out-performs the DTW-based baseline, and is competitive with current state-of-the-art spoken term discovery systems.

Mots clés: Unsupervised; Spoken term discovery; Word discovery; Word segmentation

Domaines: Sciences cognitives; Linguistique; Informatique et langage [cs.CL]

Alexis Thual, Corentin Dancette, Julien Karadayi, Juan Benjumea, Emmanuel Dupoux. A K-nearest neighbours approach to unsupervised spoken term discovery. IEEE Spoken Language Technology SLT-2018, Dec 2018, Athènes, Greece. ⟨hal-01947953⟩