English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Self-supervised models, namely, wav2vec and its variants, have shownpromising results in various downstream tasks in the speech domain. However,their inner workings are poorly understood, calling for in-depth analyses onwhat the model learns. In this paper, we concentrate on the convolutionalfeature encoder where its latent space is often speculated to representdiscrete acoustic units. To analyze the embedding space in a reductive manner,we feed the synthesized audio signals, which is the summation of simple sinewaves. Through extensive experiments, we conclude that various information isembedded inside the feature encoder representations: (1) fundamental frequency,(2) formants, and (3) amplitude, packed with (4) sufficient temporal detail.Further, the information incorporated inside the latent representations isanalogous to spectrograms but with a fundamental difference: latentrepresentations construct a metric space so that closer representations implyacoustic similarity.

Opening the Black Box of wav2vec Feature Encoder