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

Transformers have recently become very popular for sequence-to-sequenceapplications such as machine translation and speech recognition. In this work,we propose a multi-task learning-based transformer model for low-resourcemultilingual speech recognition for Indian languages. Our proposed modelconsists of a conformer [1] encoder and two parallel transformer decoders. Weuse a phoneme decoder (PHN-DEC) for the phoneme recognition task and a graphemedecoder (GRP-DEC) to predict grapheme sequence. We consider the phonemerecognition task as an auxiliary task for our multi-task learning framework. Wejointly optimize the network for both phoneme and grapheme recognition tasksusing Joint CTC-Attention [2] training. We use a conditional decoding scheme toinject the language information into the model before predicting the graphemesequence. Our experiments show that our proposed approach can obtainsignificant improvement over previous approaches [4]. We also show that ourconformer-based dual-decoder approach outperforms both the transformer-baseddual-decoder approach and single decoder approach. Finally, We comparemonolingual ASR models with our proposed multilingual ASR approach.

Multilingual Speech Recognition for Low-Resource Indian Languages using Multi-Task conformer