Comparison of Non-parametric Bayesian Mixture Models for Syllable Clustering and Zero-Resource Speech Processing

Loading...
Thumbnail Image

Access rights

openAccess

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2017-08

Major/Subject

Mcode

Degree programme

Language

en

Pages

5
2744-2748

Series

Proceedings of Interspeech 2017, Interspeech: Annual Conference of the International Speech Communication Association

Abstract

Zero-resource speech processing (ZS) systems aim to learn structural representations of speech without access to labeled data. A starting point for these systems is the extraction of syllable tokens utilizing the rhythmic structure of a speech signal. Several recent ZS systems have therefore focused on clustering such syllable tokens into linguistically meaningful units. These systems have so far used heuristically set number of clusters, which can, however, be highly dataset dependent and cannot be optimized in actual unsupervised settings. This paper focuses on improving the flexibility of ZS systems using Bayesian non-parametric (BNP) mixture models that are capable of simultaneously learning the cluster models as well as their number based on the properties of the dataset. We also compare different model design choices, namely priors over the weights and the cluster component models, as the impact of these choices is rarely reported in the previous studies. Experiments are conducted using conversational speech from several languages. The models are first evaluated in a separate syllable clustering task and then as a part of a full ZS system in order to examine the potential of BNP methods and illuminate the relative importance of different model design choices.

Description

Keywords

Non-parametric clustering, zero-resource processing, variational inference, Pitman-Yor process, von Mises-Fisher mixtures

Other note

Citation

Seshadri, S, Remes, U & Räsänen, O 2017, Comparison of Non-parametric Bayesian Mixture Models for Syllable Clustering and Zero-Resource Speech Processing . in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH . vol. 2017-August, Interspeech: Annual Conference of the International Speech Communication Association, International Speech Communication Association (ISCA), pp. 2744-2748, Interspeech, Stockholm, Sweden, 20/08/2017 . https://doi.org/10.21437/Interspeech.2017-339