Analysing Discrete Self Supervised Speech Representation for Spoken Language Modeling

Amitay Sicherman, Yossi Adi

Research output: Contribution to journalConference articlepeer-review

7 Scopus citations

Abstract

This work profoundly analyzes discrete self-supervised speech representations (units) through the eyes of Generative Spoken Language Modeling (GSLM). Following the findings of such an analysis, we propose practical improvements to the discrete unit for the GSLM. First, we start comprehending these units by analyzing them in three axes: interpretation, visualization, and resynthesis. Our analysis finds a high correlation between the speech units to phonemes and phoneme families, while their correlation with speaker or gender is weaker. Additionally, we found redundancies in the extracted units and claim that one reason may be the units' context. Following this analysis, we propose a new, unsupervised metric to measure unit redundancies. Finally, we use this metric to develop new methods that improve the robustness of units' clustering and show significant improvement considering zero-resource speech metrics such as ABX. Code and analysis tools are available under the following link.

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Funding

We would like to acknowledge support for this research from the Israeli Science Foundation (ISF grant 2049/22).

FundersFunder number
Israel Science Foundation2049/22

    Keywords

    • generative spoken language modeling
    • self supervised learning
    • speech LM
    • textless NLP

    Fingerprint

    Dive into the research topics of 'Analysing Discrete Self Supervised Speech Representation for Spoken Language Modeling'. Together they form a unique fingerprint.

    Cite this