SpeechAudio Deep Neural Ntwk

3 Credits · Level: Graduate, Undergraduate

This course covers modern deep learning approaches for speech recognition, synthesis, and audio processing. Students learn PyTorch implementation of neural architectures, from foundational networks to state-of-the-art transformer models. Topics include basic text processing, audio feature extraction, automatic speech recognition, text-to-speech synthesis, and audio/music generation. The course emphasizes hands-on experience through weekly programming assignments using PyTorch. Prior programming experience in Python required; no previous signal processing or deep learning experience assumed. Designed for computational linguistics and computer science graduate students or advanced undergraduates.