Current Volume 4
Speech is the natural and most important form of communication for human beings. Speech-To-Text (STT) system takes a human speech utterance as an input and requires string of words as output. The objective of this system is to extract, characterized and recognize information about speech. Past research in mathematics, acoustic and speech technology have provided many methods for converting data that can be considered as information if interpreted correctly. In order to find some statistical relevant information from incoming data, it is important to have mechanism for reducing the information in each segment in audio signal into a relatively small no of parameters, or features. Audio features extraction serves as the basic for a wide range of applications in the areas of speech processing, multimedia data management and distribution, security, biometric and bioacoustics. The features can be extracted either directly from the time domain signal or from the transformation domain depending upon choice of the signal analysis approach.
Kotlin, RecognizerIntent, Speech-To-Text, Audio
Komal D. Pednekar , Romila R. Hotekar , Aaditi A. Shivalkar , Mandar S. Joshi "Kotlin Framework for Number Retrieval from Phone Call" Iconic Research And Engineering Journals Volume 4 Issue 11 2021 Page 22-28
Komal D. Pednekar , Romila R. Hotekar , Aaditi A. Shivalkar , Mandar S. Joshi "Kotlin Framework for Number Retrieval from Phone Call" Iconic Research And Engineering Journals, 4(11)