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

This paper presents a speech recognition system developed by the TranssionSpeech Understanding Processing Team (TSUP) for the ASRU 2023 MADASR Challenge.The system focuses on adapting ASR models for low-resource Indian languages andcovers all four tracks of the challenge. For tracks 1 and 2, the acoustic modelutilized a squeezeformer encoder and bidirectional transformer decoder withjoint CTC-Attention training loss. Additionally, an external KenLM languagemodel was used during TLG beam search decoding. For tracks 3 and 4, pretrainedIndicWhisper models were employed and finetuned on both the challenge datasetand publicly available datasets. The whisper beam search decoding was alsomodified to support an external KenLM language model, which enabled betterutilization of the additional text provided by the challenge. The proposedmethod achieved word error rates (WER) of 24.17%, 24.43%, 15.97%, and 15.97%for Bengali language in the four tracks, and WER of 19.61%, 19.54%, 15.48%, and15.48% for Bhojpuri language in the four tracks. These results demonstrate theeffectiveness of the proposed method.

Transsion TSUP's speech recognition system for ASRU 2023 MADASR Challenge