Comparison of syllabification algorithms and training strategies for robust word count estimation across different languages and recording conditions

Okko Räsänen, Shreyas Seshadri, Marisa Casillas

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

    5 Citations (Scopus)
    235 Downloads (Pure)

    Abstract

    Word count estimation (WCE) from audio recordings has a number of applications, including quantifying the amount of speech that language-learning infants hear in their natural environments, as captured by daylong recordings made with devices worn by infants. To be applicable in a wide range of scenarios and also low-resource domains, WCE tools should be extremely robust against varying signal conditions and require minimal access to labeled training data in the target domain. For this purpose, earlier work has used automatic syllabification of speech, followed by a least-squares-mapping of syllables to word counts. This paper compares a number of previously proposed syllabifiers in the WCE task, including a supervised bi-directional long short-term memory (BLSTM) network that is trained on a language for which high quality syllable annotations are available (a “high resource language”), and reports how the alternative methods compare on different languages and signal conditions. We also explore additive noise and varying-channel data augmentation strategies for BLSTM training, and show how they improve performance in both matching and mismatching languages. Intriguingly, we also find that even though the BLSTM works on languages beyond its training data, the unsupervised algorithms can still outperform it in challenging signal conditions on novel languages.

    Original languageEnglish
    Title of host publicationProceedings of Interspeech
    PublisherInternational Speech Communication Association (ISCA)
    Pages1200-1204
    Number of pages5
    Volume2018-September
    DOIs
    Publication statusPublished - 1 Jan 2018
    MoE publication typeA4 Conference publication
    EventInterspeech - Hyderabad International Convention Centre, Hyderabad, India
    Duration: 2 Sept 20186 Sept 2018
    http://interspeech2018.org/

    Publication series

    NameProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
    PublisherInternational Speech Communication Association
    ISSN (Print)2308-457X

    Conference

    ConferenceInterspeech
    Country/TerritoryIndia
    CityHyderabad
    Period02/09/201806/09/2018
    Internet address

    Keywords

    • Daylong recordings
    • Language acquisition
    • Noise robustness
    • Syllabification
    • Word count estimation

    Fingerprint

    Dive into the research topics of 'Comparison of syllabification algorithms and training strategies for robust word count estimation across different languages and recording conditions'. Together they form a unique fingerprint.

    Cite this