Robust voice activity detection using DNN approaches

• Main Author: Parashar Kshitij
• Other Authors: Chng Eng Siong
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Computer and Information Science; Voice activity detection; Single channel audio; Machine learning; Deep learning; Artificial intelligence; Pyannote; Silero; Marblenet; Speech activity detection; Hyperparameter tuning; Open neural network exchange; Kaldi toolkit
• Online Access: https://hdl.handle.net/10356/175226
• Institution: Nanyang Technological University

Voice activity detection (VAD) is a pivotal component in various speech processing applications, playing a crucial role in tasks such as speech recognition, speaker diarization, and noise suppression. Recognizing its significance, this thesis delves into the exploration of advancements in single-cha...