Physiological Model Of Speech Production & Commonly Used Descriptors For Speech Analytics

Analysis of sound can be used across various areas like security management, medical diagnosis and sentiment & speech analysis for contact centers. To derive insights from sound we must first convert it into digital signals. Insight can then be used to classify calls, trigger alerts or workflows, understand sentiments, and drive operational & employee performance across the enterprise. But to achieve all this, we need to first understand details of speech production and methods to extract relevant information. This white paper discusses how speech is generated by the human body, the different ways of extracting features out of sound and the possible applications of sound analysis.