Glottal Source
The glottal source, the sound produced by the vocal folds' vibration, is a crucial element in speech and voice production, with research focusing on accurately modeling and estimating its parameters for applications such as speech synthesis and pathology detection. Current research employs diverse approaches, including advanced signal processing techniques (like inverse filtering and ARMAX models), machine learning algorithms (such as support vector machines and deep neural networks), and multimodal analysis integrating audio and video data. Understanding the glottal source is vital for improving speech technology, diagnosing voice disorders, and advancing our knowledge of human vocalization.
Papers
Investigation of Self-supervised Pre-trained Models for Classification of Voice Quality from Speech and Neck Surface Accelerometer Signals
Sudarsana Reddy Kadiri, Farhad Javanmardi, Paavo Alku
Characterization of cough sounds using statistical analysis
Naveenkumar Vodnala, Pratap Reddy Lankireddy, Padmasai Yarlagadda