Attempt Towards Stress Transfer in Speech-to-Speech Machine Translation
This work addresses the lack of intonation in SSMT systems for educational content in India, which is an incremental improvement aimed at enhancing accessibility and engagement for non-English speakers.
The paper tackled the problem of monotonous speech-to-speech machine translation (SSMT) by introducing a stress detection model and a stress-aware TTS architecture, resulting in an Indian English-to-Hindi SSMT system that transfers stress to improve engagement, though no concrete performance numbers are provided.
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.