An unsupervised method for speech detection and segmentation in noisy environments using the parametric trajectory model

This study investigates the use of the parametric trajectory model to perform unsupervised speech detection and segmentation in noisy audio files. The process of detecting and segmenting speech is subdivided into two primary tasks: the binary distinction of speech and noise, and the ability to identify the beginning and end of speech segments. For each of these two tasks, the parametric trajectory model algorithm is applied in both a model-based (prior training) and a blind (no training) approach.;The results show that the parametric trajectory model can be applied to detect and segment speech in noisy audio with a high degree of success. Additionally, the results show that the algorithm performs best when applied in the model approach. The model approach outperformed the blind approach in the identification task by 9% and 2% in the boundary detection task.