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

In this paper, we present specially designed automatic speech recognition(ASR) systems for the highly agglutinative and inflective languages of Tamiland Kannada that can recognize unlimited vocabulary of words. We use subwordsas the basic lexical units for recognition and construct subword grammarweighted finite state transducer (SG-WFST) graphs for word segmentation thatcaptures most of the complex word formation rules of the languages. We haveidentified the following category of words (i) verbs, (ii) nouns, (ii)pronouns, and (iv) numbers. The prefix, infix and suffix lists of subwords arecreated for each of these categories and are used to design the SG-WFST graphs.We also present a heuristic segmentation algorithm that can even segmentexceptional words that do not follow the rules encapsulated in the SG-WFSTgraph. Most of the data-driven subword dictionary creation algorithms arecomputation driven, and hence do not guarantee morpheme-like units and so wehave used the linguistic knowledge of the languages and manually created thesubword dictionaries and the graphs. Finally, we train a deep neural networkacoustic model and combine it with the pronunciation lexicon of the subworddictionary and the SG-WFST graph to build the subword-ASR systems. Since thesubword-ASR produces subword sequences as output for a given test speech, wepost-process its output to get the final word sequence, so that the actualnumber of words that can be recognized is much higher. Upon experimenting thesubword-ASR system with the IISc-MILE Tamil and Kannada ASR corpora, we observean absolute word error rate reduction of 12.39% and 13.56% over the baselineword-based ASR systems for Tamil and Kannada, respectively.

Knowledge-driven Subword Grammar Modeling for Automatic Speech Recognition in Tamil and Kannada