A Segmentation-based Token Identification for Recognition of Audio Mathematical Expression

In human-computer interaction, humans can interact with the computer help of text, audio, images, speech, etc. Interacting using speech recognitions in particularly audio segmentation is a challenging task due to accent or way pronouncing style. To input mathematical symbols, words, functions, and expressions keyboard are tedious time-consuming. Input this speeds up process. paper, an SBTI (audio Segmentation Based Token Identification) algorithm proposed for recognition words expression. 6 types considered recognition. The segments file into chunks from each chunk temporal spectral characteristics signals selected extract features. model trained neural network. shows classification accuracy 100% algebraic, quadratic, area, differentiation expression, 99% trigonometric 92% summation