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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Language Identification (LID) is a crucial preliminary process in the fieldof Automatic Speech Recognition (ASR) that involves the identification of aspoken language from audio samples. Contemporary systems that can processspeech in multiple languages require users to expressly designate one or morelanguages prior to utilization. The LID task assumes a significant role inscenarios where ASR systems are unable to comprehend the spoken language inmultilingual settings, leading to unsuccessful speech recognition outcomes. Thepresent study introduces convolutional recurrent neural network (CRNN) basedLID, designed to operate on the Mel-frequency Cepstral Coefficient (MFCC)characteristics of audio samples. Furthermore, we replicate certainstate-of-the-art methodologies, specifically the Convolutional Neural Network(CNN) and Attention-based Convolutional Recurrent Neural Network (CRNN withattention), and conduct a comparative analysis with our CRNN-based approach. Weconducted comprehensive evaluations on thirteen distinct Indian languages andour model resulted in over 98\% classification accuracy. The LID model exhibitshigh-performance levels ranging from 97% to 100% for languages that arelinguistically similar. The proposed LID model exhibits a high degree ofextensibility to additional languages and demonstrates a strong resistance tonoise, achieving 91.2% accuracy in a noisy setting when applied to a EuropeanLanguage (EU) dataset.

Is Attention always needed? A Case Study on Language Identification from Speech