Byakto Speech: Real-time long speech synthesis with convolutional neural network: Transfer learning from English to Bangla
This work addresses the lack of effective speech synthesis tools for Bangla speakers, though it is incremental as it adapts existing methods to a new language.
The authors tackled the challenge of real-time long speech synthesis for Bangla, a low-resource language, by developing Byakta, the first open-source bilingual TTS system, and introduced an automated scoring metric and benchmark dataset for evaluation.
Speech synthesis is one of the challenging tasks to automate by deep learning, also being a low-resource language there are very few attempts at Bangla speech synthesis. Most of the existing works can't work with anything other than simple Bangla characters script, very short sentences, etc. This work attempts to solve these problems by introducing Byakta, the first-ever open-source deep learning-based bilingual (Bangla and English) text to a speech synthesis system. A speech recognition model-based automated scoring metric was also proposed to evaluate the performance of a TTS model. We also introduce a test benchmark dataset for Bangla speech synthesis models for evaluating speech quality. The TTS is available at https://github.com/zabir-nabil/bangla-tts