Work PyTorch Project Template A template for the development of production-level structured configurable code. HiFi-VC Reproduction of a state-of-the-art voice conversion system. Audio Deepfake Detection Systems Reproduction of state-of-the-art audio deepfake detection systems, including LCNN, RawNet2, and AASIST. Courseworks Audio-Visual Speech Separation and Recognition The project aims on the development of an Audio-Visual Speech Separation and Recognition (AVSSR) system for edge devices. University Projects Fastspeech 2 Implementation of FastSpeech 2 Text-To-Speech System. HiFi-GAN Implementation of HiFi-GAN vocoder. Optimization of a Keyword Spotting System Reducing computational costs of keyword spotting system inference using distillation, pruning, and quantization. Automatic Speech Recognition Implementation of a LSTM-based automatic speech recognition system and DeepSpeech 2.