Recently, I have built the TTS system, more specifically, using Tacotron2. In particular, I built TTS system for the call-center back in USA. So, I can help with this. Along with this, I have expertise in Python-based Deep Learning.
For your reference please find my profile summary -
-> I have worked on the various state-of-the-art mapping functions using Machine Learning (ML) techniques and Deep Learning (DL) architectures. My main expertise lies in the domain of generative models, especially in Generative Adversarial Network (GAN)-based algorithm. With this, I have experienced in building various DL architectures such as DNN, CNN, ResNet, etc. I am proficient with the Pytorch library and also have knowledge of Keras and Tensorflow Libraries. Along with this, I am comfortable working with Python, MATLAB, shell scripts, etc.
-> My major experience lies in the applications of various DL techniques in the domain of speech. My research work mainly includes applications of DL-based techniques in speech pathology and voice conversion domain. With this experience, I have published quality research papers in prestigious conferences.