Paper Info
Title
An Embedded Segmental K-Means Model For Unsupervised Segmentation And Clustering Of Speech
Abstract
Unsupervised segmentation and clustering of unlabelled speech are core problems in zero-resource speech processing. Most approaches lie at methodological extremes: some use probabilistic Bayesian models with convergence guarantees, while others opt for more efficient heuristic techniques. Despite competitive performance in previous work, the full Bayesian approach is difficult to scale to large speech corpora. We introduce an approximation to a recent Bayesian model that still has a clear objective function but improves efficiency by using hard clustering and segmentation rather than full Bayesian inference. Like its Bayesian counterpart, this embedded segmental K-means model (ES-KMeans) represents arbitrary-length word segments as fixed-dimensional acoustic word embeddings. We first compare ES-KMeans to previous approaches on common English and Xitsonga data sets (5 and 2.5 hours of speech): ES-KMeans outperforms a leading heuristic method in word segmentation, giving similar scores to the Bayesian model while being 5 times faster with fewer hyperparameters. However, its clusters are less pure than those of the other models. We then show that ES-KMeans scales to larger corpora by applying it to the 5 languages of the Zero Resource Speech Challenge 2017 (up to 45 hours), where it performs competitively compared to the challenge baseline.
Year
DOI
Venue
2017
10.1109/asru.2017.8269008
2017 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU)
Keywords
DocType
Volume
Zero-resource speech processing, word segmentation, unsupervised learning, language acquisition
Conference
abs/1703.08135
Citations 
PageRank 
References 
4
0.37
21
Authors
3
Name
Order
Citations
PageRank
Herman Kamper115020.70
Karen Livescu2125471.43
Sharon Goldwater31437103.96