S. Akarsh

Sai Akarsh, Vamshi Raghusimha, Anindita Mondal et al.

The language diversity in India's education sector poses a significant challenge, hindering inclusivity. Despite the democratization of knowledge through online educational content, the dominance of English, as the internet's lingua franca, limits accessibility, emphasizing the crucial need for translation into Indian languages. Despite existing Speech-to-Speech Machine Translation (SSMT) technologies, the lack of intonation in these systems gives monotonous translations, leading to a loss of audience interest and disengagement from the content. To address this, our paper introduces a dataset with stress annotations in Indian English and also a Text-to-Speech (TTS) architecture capable of incorporating stress into synthesized speech. This dataset is used for training a stress detection model, which is then used in the SSMT system for detecting stress in the source speech and transferring it into the target language speech. The TTS architecture is based on FastPitch and can modify the variances based on stressed words given. We present an Indian English-to-Hindi SSMT system that can transfer stress and aim to enhance the overall quality and engagement of educational content.

Vidya Prasad K, Akarsh S, Vinayakumar R et al.

Deep learning mechanisms are prevailing approaches in recent days for the various tasks in natural language processing, speech recognition, image processing and many others. To leverage this we use deep learning based mechanism specifically Bidirectional- Long Short-Term Memory (B-LSTM) for the task of dialectic identification in Arabic and German broadcast speech and Long Short-Term Memory (LSTM) for discriminating between similar Languages. Two unique B-LSTM models are created using the Large-vocabulary Continuous Speech Recognition (LVCSR) based lexical features and a fixed length of 400 per utterance bottleneck features generated by i-vector framework. These models were evaluated on the VarDial 2017 datasets for the tasks Arabic, German dialect identification with dialects of Egyptian, Gulf, Levantine, North African, and MSA for Arabic and Basel, Bern, Lucerne, and Zurich for German. Also for the task of Discriminating between Similar Languages like Bosnian, Croatian and Serbian. The B-LSTM model showed accuracy of 0.246 on lexical features and accuracy of 0.577 bottleneck features of i-Vector framework.