Unsupervised discovery of recurring speech patterns using probabilistic adaptive metrics

Okko Räsänen, María Andrea Cruz Blandón

    Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

    20 Citations (Scopus)
    154 Downloads (Pure)

    Abstract

    Unsupervised spoken term discovery (UTD) aims at finding recurring segments of speech from a corpus of acoustic speech data. One potential approach to this problem is to use dynamic time warping (DTW) to find well-aligning patterns from the speech data. However, automatic selection of initial candidate segments for the DTW-alignment and detection of “sufficiently good” alignments among those require some type of predefined criteria, often operationalized as threshold parameters for pair-wise distance metrics between signal representations. In the existing UTD systems, the optimal hyperparameters may differ across datasets, limiting their applicability to new corpora and truly low-resource scenarios. In this paper, we propose a novel probabilistic approach to DTW-based UTD named as PDTW. In PDTW, distributional characteristics of the processed corpus are utilized for adaptive evaluation of alignment quality, thereby enabling systematic discovery of pattern pairs that have similarity what would be expected by coincidence. We test PDTW on Zero Resource Speech Challenge 2017 datasets as a part of 2020 implementation of the challenge. The results show that the system performs consistently on all five tested languages using fixed hyperparameters, clearly outperforming the earlier DTW-based system in terms of coverage of the detected patterns.

    Original languageEnglish
    Title of host publicationProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
    PublisherInternational Speech Communication Association (ISCA)
    Pages4871-4875
    Number of pages5
    Volume2020-October
    DOIs
    Publication statusPublished - 2020
    MoE publication typeA4 Conference publication
    EventInterspeech - Shanghai, China
    Duration: 25 Oct 202029 Oct 2020
    Conference number: 21
    http://www.interspeech2020.org/

    Publication series

    NameInterspeech
    PublisherInternational Speech Communication Association
    ISSN (Print)2308-457X

    Conference

    ConferenceInterspeech
    Abbreviated titleINTERSPEECH
    Country/TerritoryChina
    CityShanghai
    Period25/10/202029/10/2020
    Internet address

    Keywords

    • Dynamic time warping
    • Pattern matching
    • Unsupervised learning
    • Zero resource speech processing

    Fingerprint

    Dive into the research topics of 'Unsupervised discovery of recurring speech patterns using probabilistic adaptive metrics'. Together they form a unique fingerprint.

    Cite this