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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper explains our work in developing new acoustic models for automatedspeech recognition (ASR) at KBLab, the infrastructure for data-driven researchat the National Library of Sweden (KB). We evaluate different approaches for aviable speech-to-text pipeline for audiovisual resources in Swedish, using thewav2vec 2.0 architecture in combination with speech corpuses created from KB'scollections. These approaches include pretraining an acoustic model for Swedishfrom the ground up, and fine-tuning existing monolingual and multilingualmodels. The collections-based corpuses we use have been sampled from millionsof hours of speech, with a conscious attempt to balance regional dialects toproduce a more representative, and thus more democratic, model. The acousticmodel this enabled, "VoxRex", outperforms existing models for Swedish ASR. Wealso evaluate combining this model with various pretrained language models,which further enhanced performance. We conclude by highlighting the potentialof such technology for cultural heritage institutions with vast collections ofpreviously unlabelled audiovisual data. Our models are released for furtherexploration and research here: https://huggingface.co/KBLab.

Hearing voices at the National Library -- a speech corpus and acoustic model for the Swedish language