Treebanks are linguistically annotated corpus of natural language texts represented as a database. It is vital in natural language processing (NLP), which allows the interaction and communication between computers and the human language. It is behind the recent technological innovations of automated and smart assistants. This paper intends to create an English treebank for the usage of Mapua University in their future endeavors to develop Interactive Voice Response (IVR) systems. This study is accomplished by providing students with a connection to a communication server through their phones. Calls are made to the Asterisk server set up in a Raspberry Pi. When the intended audio message is forwarded to the system, it is converted to a text input using a Speech-to-Text algorithm. It then undergoes process and analysis divided into five parts: preprocessing, segmentation, tagging, creation of the grammar tree, and computation for the Probabilistic Context-Free Grammar (PCFG). Based on the testing results for this study, the system yielded a word error rate of 7.36%, a NER F1 score of 71.7%, and a PCFG calculation accuracy of 64.44%.